Valkolakki vai haalarit, vaiko molemmat : Koulutuspolitiikan vaikuttajien näkemykset toisen asteen kehityksestä

In the present research Finnish education policy-makers describe the transformation in upper secondary education in the 1990s. They answered questions related to equality and all-round education. The timeline of the research extends from the early development of the welfare state and equality policy to the 2000s. Its focus is on upper secondary education, which, in this paper, denotes general upper secondary education and vocational upper secondary education. The chronological analysis proceeds from the education committee of 1971 up to the youth education experiment of the 1990s. The voices of the then policy-makers are heard in this research. They were the ones who planned the reforms and/or made the decisions. This being the case, the interviewees include cabinet ministers, permanent secretaries, representatives of organisations and the research community as well as civil servants. The research material can be construed as contextual interpretations of the past, influenced by both the times and places where the narrations were given. The persons interviewed described their experiences and views on education policy. In their narratives they illustrated the transformation that occurred in relation to equality and all-round education. The narrative interviews painted a picture of the upper secondary education transformation and the matriculation examination as having a slowing effect on education policy reforms. It was not until the 1990s when the said examination began to make a difference to students in vocational upper secondary education Those interviewed named the persons who, in their opinion, had the most say in Finnish education policy. This list comprised a small circle of people who more or less agreed on the grand values of education policy, i.e. all-round education and equality. Only a small minority represented a radical view of equality, being true believers in universal upper secondary education implemented in accordance with comprehensive school reform. Finnish education policy was led from the perspective of traditional conception of equality from the 1970s to the 1980s. The transformation finally occurred in the 1990s when equality was understood to mean individual needs and the right to choose. As was the case with matriculation education, the insistence on all-round education also hampered the development of universal upper secondary education. The interviews revealed that any attempts to increase the academic syllabus of vocational education caused organisations as well as other policy-makers to oppose such development well into the 1980s. It was not until the youth education experiment of the 1990s that vocational education finally carved a path to higher education, when the polytechnic schools were made permanent. Three principal groups of key players emerged in the research: ministers of education, civil servants and organisations. The research showed that the ministers and civil servant education policy-makers of the 1990s also included only handful women. The circle of policy-makers was small and represented similar schools of thought. In the 1970s era of government committees, representatives of organisations actively participated in education policy. When the committee establishment was discontinued, this eliminated lobbying venues for the organisations. Nonetheless, the organisations regained their policymaking status in the 1990s. New lobbying organisations included the Finnish Entrepreneurs and the Union of Finnish Upper Secondary School Students. However, in contrast to the 1970s, only rarely would individuals rise from the ranks of organisations to the cadre of policy-makers. The interviewees had a twofold view of neo-liberalism Contrary to other policy-makers, representatives of the research community and organisations concur that neo-liberalism did exist in education policy decision-making in the 1990s.

Solution concepts in continuous-kernel multicriteria games

This paper considers nonzero-sum multicriteria games with continuous kernels. Solution concepts based on the notions of Pareto optimality, equilibrium, and security are extended to these games. Separate necessary and sufficient conditions and existence results are presented for equilibrium, Pareto-optimal response, and Pareto-optimal security strategies of the players.

GATA Factors Regulate Inner Ear Development and Midbrain Neurogenesis

The zinc-finger transcription factors GATA2 and GATA3 in vertebrates belong to the six-member family that are essential regulators in the development of various organs. The aim of this study was to gain new information of the roles of GATA2 and GATA3 in inner ear morphogenesis and of the function of GATA2 in neuronal fate specification in the midbrain using genetically modified mouse and chicken embryos as models. A century ago the stepwise process of inner ear epithelial morphogenesis was described, but the molecular players regulating the cellular differentiation of the otic epithelium are still not fully resolved. This study provided novel data on GATA factor roles in several developmental processes during otic development. The expression analysis in chicken suggested that GATA2 and GATA3 possess redundant roles during otic cup and vesicle formation, but complementary cell-type specific functions during vestibular and cochlear morphogenesis. The comparative analysis between mouse and chicken Gata2 and Gata3 expression revealed many conserved aspects, especially during later stages of inner ear development, while the expression was more divergent at early stages. Namely, expression of both Gata genes was initiated earlier in chicken than mouse otic epithelium relative to the morphogenetic stages. Likewise, important differences concerning Gata3 expression in the otic cup epithelium were detected between mouse and chicken, suggesting that distinct molecular mechanisms regulate otic vesicle closure in different vertebrate species. Temporally distinct Gata2 and Gata3 expression was also found during otic ganglion formation in mouse and chicken. Targeted inactivation of Gata3 in mouse embryos caused aberrant morphology of the otic vesicle that in severe cases was disrupted into two parts, a dorsal and a ventral vesicle. Detailed analyses of Gata3 mutant embryos unveiled a crucial role for GATA3 in the initial inner ear morphogenetic event, the invagination of the otic placode. A large-scale comparative expression analysis suggested that GATA3 could control cell adhesion and motility in otic epithelium, which could be important for early morphogenesis. GATA3 was also identified as the first factor to directly regulate Fgf10 expression in the otic epithelium and could thus influence the development of the semicircular ducts. Despite the serious problems in the early inner ear development, the otic sensory fate establishment and some vestibular hair cell differentiation was observable in pharmacologically rescued Gata3-/- embryos. Cochlear sensory differentiation was, however, completely blocked so that no auditory hair cells were detected. In contrast to the early morphogenetic phenotype in Gata3-/- mutants, conditional inactivation of Gata2 in mouse embryos resulted in a relatively late growth defect of the three semicircular ducts. GATA2 was required for the proliferation of the vestibular nonsensory epithelium to support growing of the three ducts. Concurrently, with the role in epithelial semicircular ducts, GATA2 was also required for the mesenchymal cell clearance from the vestibular perilymphatic region between the membranous labyrinth and bony capsule. The gamma-aminobutyric acid-secreting (GABAergic) neurons in the midbrain are clinically relevant since they contribute to fear, anxiety, and addiction regulation. The molecular mechanisms regulating the GABAergic neuronal development, however, are largely unknown. Using tissue-specific mutagenesis in mice, GATA2 was characterized as a critical determinant of the GABAergic neuronal fate in the midbrain. In Gata2-deficient mouse midbrain, GABAergic neurons were not produced, instead the Gata2-mutant cells acquired a glutamatergic neuronal phenotype. Gain-of-function experiments in chicken also revealed that GATA2 was sufficient to induce GABAergic differentiation in the midbrain.

Generation of Flat and Curved Membranes by Inverse-BAR Domain Proteins

Biological membranes are tightly linked to the evolution of life, because they provide a way to concentrate molecules into partially closed compartments. The dynamic shaping of cellular membranes is essential for many physiological processes, including cell morphogenesis, motility, cytokinesis, endocytosis, and secretion. It is therefore essential to understand the structure of the membrane and recognize the players that directly sculpt the membrane and enable it to adopt different shapes. The actin cytoskeleton provides the force to push eukaryotic plasma membrane in order to form different protrusions or/and invaginations. It has now became evident that actin directly co-operates with many membrane sculptors, including BAR domain proteins, in these important events. However, the molecular mechanisms behind BAR domain function and the differences between the members of this large protein family remain largely unresolved. In this thesis, the structure and functions of the I-BAR domain family members IRSp53 and MIM were thoroughly analyzed. By using several methods such as electron microscopy and systematic mutagenesis, we showed that these I-BAR domain proteins bind to PI(4,5)P2-rich membranes, generate negative membrane curvature and are involved in the formation of plasma membrane protrusions in cells e.g. filopodia. Importantly, we characterized a novel member of the BAR-domain superfamily which we named Pinkbar. We revealed that Pinkbar is specifically expressed in kidney and epithelial cells, and it localizes to Rab13-positive vesicles in intestinal epithelial cells. Remarkably, we learned that the I-BAR domain of Pinkbar does not generate membrane curvature but instead stabilizes planar membranes. Based on structural, mutagenesis and biochemical work we present a model for the mechanism of the novel membrane deforming activity of Pinkbar. Collectively, this work describes the mechanism by which I-BAR domain proteins deform membranes and provides new information about the biological roles of these proteins. Intriguingly, this work also gives evidence that significant functional plasticity exists within the I-BAR domain family. I-BAR proteins can either generate negative membrane curvature or stabilize planar membrane sheets, depending on the specific structural properties of their I-BAR domains. The results presented in this thesis expand our knowledge on membrane sculpting mechanisms and shows for the first time how flat membranes can be generated in cells.

Lasten sitoutuneisuus toimintaan : kvantitatiivinen havainnointitutkimus

Children s involvement is a key quality factor in Early Years Education. As a process variable it concentrates on children s actions and experiences. The involved children are operating in their zone of proximal development. The aim of this study was to find out how the children involved themselves in the Finnish day care centres. The problems of the study were: (1) how the children are involved in different situations between the hours 8.00 and 12.00, (2) how do the skills of children whose involvement level is high differ from the skills of children whose involvement level is low and (3) how do the learning environments of the children whose involvement level is high differ from the learning environments of the children whose involvement level is low? The research method was observation and children s involvement levels were assessed using LIS-YC Scale. In addition, the kindergarten teachers evaluated the children s skills and the team workers did the evaluations of the educational settings. The data used in this study was a part of the Orientaation lähteillä research. The 802 children, who took part in the study, were from 48 different groups of eight different municipalities in Central Uusimaa. There were 18358 observations of children s involvement and the quantitative data was analyzed using correlation, cross tabulation and t-test. Children s involvement was an average at a moderate level. The involvement levels were the highest during playing time and adult guided tasks and lowest during eating and basic care situations. The level of involvement was higher if the children were adaptable, proactive, self-motivated and good players. The involvement lever was lower if the children needed some special care. The children s involvement is supported if the educators had at least once a week a meeting and if children s confidence and identity construction was frequently considered in educational discussions. Furthermore, the appreciation of the ethical issues and positive atmosphere appeared to confirm the involvement. The children s involvement is decreased if the educators had been perpetually short of time or resources or there has been lack of joy and humour in the group.

Denumerable state stochastic games with limiting average payoff

We study stochastic games with countable state space, compact action spaces, and limiting average payoff. ForN-person games, the existence of an equilibrium in stationary strategies is established under a certain Liapunov stability condition. For two-person zero-sum games, the existence of a value and optimal strategies for both players are established under the same stability condition.

Identification of Critical Residues of the Mycobacterial Dephosphocoenzyme A Kinase by Site-Directed Mutagenesis

Dephosphocoenzyme A kinase performs the transfer of the c-phosphate of ATP to dephosphocoenzyme A, catalyzing the last step of coenzyme A biosynthesis. This enzyme belongs to the P-loop-containing NTP hydrolase superfamily, all members of which posses a three domain topology consisting of a CoA domain that binds the acceptor substrate, the nucleotide binding domain and the lid domain. Differences in the enzymatic organization and regulation between the human and mycobacterial counterparts, have pointed out the tubercular CoaE as a high confidence drug target (HAMAP database). Unfortunately the absence of a three-dimensional crystal structure of the enzyme, either alone or complexed with either of its substrates/regulators, leaves both the reaction mechanism unidentified and the chief players involved in substrate binding, stabilization and catalysis unknown. Based on homology modeling and sequence analysis, we chose residues in the three functional domains of the enzyme to assess their contributions to ligand binding and catalysis using site-directed mutagenesis. Systematically mutating the residues from the P-loop and the nucleotide-binding site identified Lys14 and Arg140 in ATP binding and the stabilization of the phosphoryl intermediate during the phosphotransfer reaction. Mutagenesis of Asp32 and Arg140 showed catalytic efficiencies less than 5-10% of the wild type, indicating the pivotal roles played by these residues in catalysis. Non-conservative substitution of the Leu114 residue identifies this leucine as the critical residue from the hydrophobic cleft involved in leading substrate, DCoA binding. We show that the mycobacterial enzyme requires the Mg2+ for its catalytic activity. The binding energetics of the interactions of the mutant enzymes with the substrates were characterized in terms of their enthalpic and entropic contributions by ITC, providing a complete picture of the effects of the mutations on activity. The properties of mutants defective in substrate recognition were consistent with the ordered sequential mechanism of substrate addition for CoaE.

A Shapley Value-Based Approach to Discover Influential Nodes in Social Networks

Our study concerns an important current problem, that of diffusion of information in social networks. This problem has received significant attention from the Internet research community in the recent times, driven by many potential applications such as viral marketing and sales promotions. In this paper, we focus on the target set selection problem, which involves discovering a small subset of influential players in a given social network, to perform a certain task of information diffusion. The target set selection problem manifests in two forms: 1) top-k nodes problem and 2) lambda-coverage problem. In the top-k nodes problem, we are required to find a set of k key nodes that would maximize the number of nodes being influenced in the network. The lambda-coverage problem is concerned with finding a set of k key nodes having minimal size that can influence a given percentage lambda of the nodes in the entire network. We propose a new way of solving these problems using the concept of Shapley value which is a well known solution concept in cooperative game theory. Our approach leads to algorithms which we call the ShaPley value-based Influential Nodes (SPINs) algorithms for solving the top-k nodes problem and the lambda-coverage problem. We compare the performance of the proposed SPIN algorithms with well known algorithms in the literature. Through extensive experimentation on four synthetically generated random graphs and six real-world data sets (Celegans, Jazz, NIPS coauthorship data set, Netscience data set, High-Energy Physics data set, and Political Books data set), we show that the proposed SPIN approach is more powerful and computationally efficient. Note to Practitioners-In recent times, social networks have received a high level of attention due to their proven ability in improving the performance of web search, recommendations in collaborative filtering systems, spreading a technology in the market using viral marketing techniques, etc. It is well known that the interpersonal relationships (or ties or links) between individuals cause change or improvement in the social system because the decisions made by individuals are influenced heavily by the behavior of their neighbors. An interesting and key problem in social networks is to discover the most influential nodes in the social network which can influence other nodes in the social network in a strong and deep way. This problem is called the target set selection problem and has two variants: 1) the top-k nodes problem, where we are required to identify a set of k influential nodes that maximize the number of nodes being influenced in the network and 2) the lambda-coverage problem which involves finding a set of influential nodes having minimum size that can influence a given percentage lambda of the nodes in the entire network. There are many existing algorithms in the literature for solving these problems. In this paper, we propose a new algorithm which is based on a novel interpretation of information diffusion in a social network as a cooperative game. Using this analogy, we develop an algorithm based on the Shapley value of the underlying cooperative game. The proposed algorithm outperforms the existing algorithms in terms of generality or computational complexity or both. Our results are validated through extensive experimentation on both synthetically generated and real-world data sets.

'South-South' Remittance - Poverty reduction nexus. The Case of 'Hadiya' immigrants in South Africa, as Agents of 'Constituence development' in Ethiopia, and the policy implications of their 'remittance instrument'

This thesis explores the link between South-South remittance and development. It attempts to establish improved understanding about the role of immigrants as agents of constituency growth and development. By doing so, it illuminates the dark corners of the policy implications that the unconventional development agency of immigrants might have for countries in the Organization ft Economic Cooperation and Development (OECD). The thesis problematises the existence of state-centric international cooperation as providing the recipe for failed Aid in the face of global poverty menace. In the last half a century, the relative shi' of focus to non-state actors brought about the proliferation of NGOs. That, intrun, helped improve international access to crisis situations; however, their long-term remedial impacts on poverty and development have been contested. Major misgivings for non-governmental organizations (NGOs) are, on one hand, low level goal-bound expenditures and lack of independence from influence of the state, on the other. Therefore, the thesis enterprises to empirically verify its fundamental question whether remitting immigrants constitute an alternative development agency to the traditional players: the State and NGOs. Its main arguments are: due to state's failures in bringing sustainable development in many countries of the South, the future of poverty reduction and development also rests in immigrants' remittances. Nonetheless, in the last decade, remittance security-nexus dominated its discourse. Because of that remittance was viewed as something requiring global regime and restrictions. These temptations to tightly regulate remittance flows carry the danger of overlooking its trans-boundary nature and its strong link with livelihood of the poor. Therefore, to avoid unintended consequences of interventions, there need to be clear policy that bases itself on a discursive knowledge on the issues of North-South and South-South remittances The study involved both literature based and empirical research. It employed Discourse Analysis (C as main method for the former and snow-balling as its approach for the latter. For the first part the thesis constructed three conceptual models, these are: metrological model, police model and ecological model on remittance development-nexus. Through this modeling, the thesis achieved better deconstruction on the concepts remittance, immigrants and development agency. The protagonists of each model, the values and interests they represent, and their main arguments along various lines of dichotomies have been discussed. For instance, the main treats of meteorological model include: it sees remittance as transitional economic variable which require constant speculations and global management; it acts as meteorological station for following up or predicting the level, direction, flow and movement of global remittance. It focuses on official lines and considers the state as legitimate recipient of advic and positive consequence of remittance. On the other hand, police model views remittance as beir at best, development neutral or as an illicit activity requiring global regulations and tight control. Both immigrants and remittance viewed as subversive to establishments. It gives primacy to state stable agent of development and a partner for international cooperation. The anti-thesis to the police model is supplied by ecological model, which this thesis is a part. Ecological model on remittance and immigrants argues that, tight global regulations alone cannot be a panacea for possible abuse of informal remittance system. Ecological model, not only links remittance to poverty reduction, the main trust of development, but also considers the development agency of immigrants as critical factor for 21st century north-south development intervention. It sees immigrants as development conscious and their remittance instrument as most stable flow of finance to the developing countries. Besides, it sees remittance as effective poverty solutions than Foreign Direct Investment and international AID. This thesis focuses on the significance of South-South remittance and investigates the South Africa - Ethiopia remittance corridor, as case study; and empirically verifies the role of Ethiopian (Kembata and Hadiya) immigrants in South Africa as agents of local development back home. The study involved techniques of interview, group discussions, observations and investigative study. It also looked into the determinants of their migration to South Africa, and their remittance to Ethiopia. The theoretical models in the first part of the thesis have been operationalised throughout the empirical part to verify if the Kembata and Hadiya immigrants played the crucial role in their household poverty and local development in comparison with the Ethiopian state and the NGOs involved in the system. As evidenced by the research the thesis has made three distinct contributions to the discourse of remittance development-nexus. Fist, it systematized the debate about linkages between remittance, immigrants, development agency and policy of international cooperation by creating three conceptual models (school of thoughts); second, it singled out remitting immigrants as new agents of development in the South; third, it deconstructed concept of remittance and established South¬South remittance as additional sphere of academic investigation. In addition to the above contributions, the thesis finds that Kembata and Hadiya immigrants have engaged in various developmental activities in their locality than usually anticipated. Hence, it concludes that Ethiopian immigrants constitute an alternative development agency to the state and other non-state actors in their country, and the lesson can be applied to poverty reduction strategies in most developing countries.

A non-cooperative game-theoretic approach to channel assignment in multi-channel multi-radio wireless networks

Channel assignment in multi-channel multi-radio wireless networks poses a significant challenge due to scarcity of number of channels available in the wireless spectrum. Further, additional care has to be taken to consider the interference characteristics of the nodes in the network especially when nodes are in different collision domains. This work views the problem of channel assignment in multi-channel multi-radio networks with multiple collision domains as a non-cooperative game where the objective of the players is to maximize their individual utility by minimizing its interference. Necessary and sufficient conditions are derived for the channel assignment to be a Nash Equilibrium (NE) and efficiency of the NE is analyzed by deriving the lower bound of the price of anarchy of this game. A new fairness measure in multiple collision domain context is proposed and necessary and sufficient conditions for NE outcomes to be fair are derived. The equilibrium conditions are then applied to solve the channel assignment problem by proposing three algorithms, based on perfect/imperfect information, which rely on explicit communication between the players for arriving at an NE. A no-regret learning algorithm known as Freund and Schapire Informed algorithm, which has an additional advantage of low overhead in terms of information exchange, is proposed and its convergence to the stabilizing outcomes is studied. New performance metrics are proposed and extensive simulations are done using Matlab to obtain a thorough understanding of the performance of these algorithms on various topologies with respect to these metrics. It was observed that the algorithms proposed were able to achieve good convergence to NE resulting in efficient channel assignment strategies.

Absolutely expedient algorithms for learning Nash equilibria

This paper considers a multi-person discrete game with random payoffs. The distribution of the random payoff is unknown to the players and further none of the players know the strategies or the actual moves of other players. A class of absolutely expedient learning algorithms for the game based on a decentralised team of Learning Automata is presented. These algorithms correspond, in some sense, to rational behaviour on the part of the players. All stable stationary points of the algorithm are shown to be Nash equilibria for the game. It is also shown that under some additional constraints on the game, the team will always converge to a Nash equilibrium.

Stochastic differential games: Occupation measure based approach

A new approach based on occupation measures is introduced for studying stochastic differential games. For two-person zero-sum games, the existence of values and optimal strategies for both players is established for various payoff criteria. ForN-person games, the existence of equilibria in Markov strategies is established for various cases.

Angelman Syndrome Protein UBE3A Interacts with Primary Microcephaly Protein ASPM, Localizes to Centrosomes and Regulates Chromosome Segregation

Many proteins associated with the phenotype microcephaly have been localized to the centrosome or linked to it functionally. All the seven autosomal recessive primary microcephaly (MCPH) proteins localize at the centrosome. Microcephalic osteodysplastic primordial dwarfism type II protein PCNT and Seckel syndrome (also characterized by severe microcephaly) protein ATR are also centrosomal proteins. All of the above findings show the importance of centrosomal proteins as the key players in neurogenesis and brain development. However, the exact mechanism as to how the loss-of-function of these proteins leads to microcephaly remains to be elucidated. To gain insight into the function of the most commonly mutated MCPH gene ASPM, we used the yeast two-hybrid technique to screen a human fetal brain cDNA library with an ASPM bait. The analysis identified Angelman syndrome gene product UBE3A as an ASPM interactor. Like ASPM, UBE3A also localizes to the centrosome. The identification of UBE3A as an ASPM interactor is not surprising as more than 80% of Angelman syndrome patients have microcephaly. However, unlike in MCPH, microcephaly is postnatal in Angelman syndrome patients. Our results show that UBE3A is a cell cycle regulated protein and its level peaks in mitosis. The shRNA knockdown of UBE3A in HEK293 cells led to many mitotic abnormalities including chromosome missegregation, abnormal cytokinesis and apoptosis. Thus our study links Angelman syndrome protein UBE3A to ASPM, centrosome and mitosis for the first time. We suggest that a defective chromosome segregation mechanism is responsible for the development of microcephaly in Angelman syndrome.

Probing the Allosteric Mechanism in Pyrrolysyl-tRNA Synthetase Using Energy-Weighted Network Formalism

Pyrrolysyl-tRNA synthetase (PyIRS) is an atypical enzyme responsible for charging tRNA(Pyl) with pyrrolysine, despite lacking precise tRNA anticodon recognition. This dimeric protein exhibits allosteric regulation of function, like any other tRNA synthetases. In this study we examine the paths of allosteric communication at the atomic level, through energy-weighted networks of Desulfitobacterium hafniense PyIRS (DhPyIRS) and its complexes with tRNA(Pyl) and activated pyrrolysine. We performed molecular dynamics simulations of the structures of these complexes to obtain an ensemble conformation-population perspective. Weighted graph parameters relevant to identifying key players and ties in the context of social networks such as edge/node betweenness, closeness index, and the concept of funneling are explored in identifying key residues and interactions leading to shortest paths of communication in the structure networks of DhPylRS. Further, the changes in the status of important residues and connections and the costs of communication due to ligand induced perturbations are evaluated. The optimal, suboptimal, and preexisting paths are also investigated. Many of these parameters have exhibited an enhanced asymmetry between the two subunits of the dimeric protein, especially in the pretransfer complex, leading us to conclude that encoding of function goes beyond the sequence/structure of proteins. The local and global perturbations mediated by appropriate ligands and their influence on the equilibrium ensemble of conformations also have a significant role to play in the functioning of proteins. Taking a comprehensive view of these observations, we propose that the origin of many functional aspects (allostery rand half-sites reactivity in the case of DhPyIRS) lies in subtle rearrangements of interactions and dynamics at a global level.

A game theoretic approach for feature clustering and its application to feature selection

In this paper, we develop a game theoretic approach for clustering features in a learning problem. Feature clustering can serve as an important preprocessing step in many problems such as feature selection, dimensionality reduction, etc. In this approach, we view features as rational players of a coalitional game where they form coalitions (or clusters) among themselves in order to maximize their individual payoffs. We show how Nash Stable Partition (NSP), a well known concept in the coalitional game theory, provides a natural way of clustering features. Through this approach, one can obtain some desirable properties of the clusters by choosing appropriate payoff functions. For a small number of features, the NSP based clustering can be found by solving an integer linear program (ILP). However, for large number of features, the ILP based approach does not scale well and hence we propose a hierarchical approach. Interestingly, a key result that we prove on the equivalence between a k-size NSP of a coalitional game and minimum k-cut of an appropriately constructed graph comes in handy for large scale problems. In this paper, we use feature selection problem (in a classification setting) as a running example to illustrate our approach. We conduct experiments to illustrate the efficacy of our approach.