Sham M. Kakade

From MaRDI portal
Person:404304

Available identifiers

zbMath Open kakade.sham-mMaRDI QIDQ404304

List of research outcomes





PublicationDate of PublicationType
Robust aggregation for federated learning2024-09-12Paper
On Nonconvex Optimization for Machine Learning2022-12-08Paper
https://portal.mardi4nfdi.de/entity/Q49990292021-07-09Paper
Recovering Structured Probability Matrices2021-06-15Paper
A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares)2020-11-25Paper
Stochastic subgradient method converges on tame functions2020-01-31Paper
Prediction with a short memory2019-08-22Paper
Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal2019-06-10Paper
Revisiting the Polyak step size2019-05-01Paper
A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm2019-02-11Paper
Minimal Realization Problems for Hidden Markov Models2019-02-07Paper
https://portal.mardi4nfdi.de/entity/Q45585622018-11-22Paper
Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting2017-07-12Paper
Robust Matrix Decomposition With Sparse Corruptions2017-07-12Paper
Learning mixtures of spherical gaussians2017-05-16Paper
Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT)2016-11-30Paper
When are overcomplete topic models identifiable? Uniqueness of tensor Tucker decompositions with structured sparsity2016-02-19Paper
Learning Mixtures of Gaussians in High Dimensions2015-08-21Paper
A spectral algorithm for latent Dirichlet allocation2015-05-21Paper
https://portal.mardi4nfdi.de/entity/Q29340622014-12-08Paper
Tensor decompositions for learning latent variable models2014-12-08Paper
https://portal.mardi4nfdi.de/entity/Q29338502014-12-08Paper
A tail inequality for quadratic forms of subgaussian random vectors2014-09-22Paper
Random design analysis of ridge regression2014-09-04Paper
Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism2014-06-26Paper
https://portal.mardi4nfdi.de/entity/Q54051762014-04-01Paper
Stochastic Convex Optimization with Bandit Feedback2013-06-27Paper
A spectral algorithm for learning hidden Markov models2012-08-17Paper
Tail inequalities for sums of random matrices that depend on the intrinsic dimension2012-06-22Paper
Online Markov Decision Processes2011-04-27Paper
Playing Games with Approximation Algorithms2010-07-07Paper
Information Consistency of Nonparametric Gaussian Process Methods2009-02-24Paper
https://portal.mardi4nfdi.de/entity/Q35496542009-01-05Paper
Multi-view Regression Via Canonical Correlation Analysis2008-01-03Paper
Deterministic calibration and Nash equilibrium2007-11-30Paper
Learning Theory2006-06-22Paper
Learning Theory2005-06-13Paper
Learning Theory2005-06-13Paper
https://portal.mardi4nfdi.de/entity/Q31488312002-09-22Paper

Research outcomes over time

This page was built for person: Sham M. Kakade