Theory

Open Problem: Does AdaBoost Always Cycle? COLT 2012 Provable ICA with Unknown Gaussian Noise, with Implications for Gaussian Mixtures and Autoencoders NeurIPS 2012 Regression for sets of polynomial equations AISTATS 2012 Smooth-projected Neighborhood Pursuit for High-dimensional Nonparanormal Graph Estimation NeurIPS 2012 Spectral Learning of General Weighted Automata via Constrained Matrix Completion NeurIPS 2012 Spectral learning of linear dynamics from generalised-linear observations with application to neural population data NeurIPS 2012 Stability of Density-Based Clustering JMLR 2012 Stochastic Bandit Based on Empirical Moments AISTATS 2012 Structured Sparsity and Generalization JMLR 2012 Submodular-Bregman and the Lovász-Bregman Divergences with Applications NeurIPS 2012 Testing for Membership to the IFRA and the NBU Classes of Distributions AISTATS 2012 The Bethe Partition Function of Log-supermodular Graphical Models NeurIPS 2012 The representer theorem for Hilbert spaces: a necessary and sufficient condition NeurIPS 2012 Toward Understanding Complex Spaces: Graph Laplacians on Manifolds with Singularities and Boundaries COLT 2012 (weak) Calibration is Computationally Hard COLT 2012 A Close Look to Margin Complexity and Related Parameters COLT 2011 A Convergence Analysis of Log-Linear Training NeurIPS 2011 Algorithms and hardness results for parallel large margin learning NeurIPS 2011 A More Powerful Two-Sample Test in High Dimensions using Random Projection NeurIPS 2011 Asymptotic Theory for Linear-Chain Conditional Random Fields AISTATS 2011 Bandits, Query Learning, and the Haystack Dimension COLT 2011 Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization COLT 2011 Bounds on Individual Risk for Log-loss Predictors COLT 2011 Comparative Analysis of Viterbi Training and Maximum Likelihood Estimation for HMMs NeurIPS 2011 Complexity of Inference in Latent Dirichlet Allocation NeurIPS 2011