Lista de obras - Sham Kakade - Dominio Público Uruguay

A Natural Policy Gradient ⬇️

artículo científico publicado en 2002

A Smoother Way to Train Structured Prediction Models ⬇️

A Spectral Algorithm for Latent Dirichlet Allocation ⬇️

A spectral algorithm for learning Hidden Markov Models

A tail inequality for quadratic forms of subgaussian random vectors ⬇️

artículo científico de 'Electronic Communications in Probability' publicado en 2012

Acquisition and extinction in autoshaping

artículo científico publicado en 2002

Acquisition in Autoshaping ⬇️

Convergence Rates of Active Learning for Maximum Likelihood Estimation ⬇️

article by Kamalika Chaudhuri et al published 2015 in Advances in Neural Information Processing Systems 28

Dopamine Bonuses ⬇️

Dopamine: generalization and bonuses

artículo científico publicado en 2002

Economic Properties of Social Networks ⬇️

artículo científico publicado en 2005

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression ⬇️

artículo científico publicado en 2011

Experts in a Markov Decision Process ⬇️

artículo científico publicado en 2005

Explaining Away in Weight Space ⬇️

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs ⬇️

artículo científico publicado en 2020

From Batch to Transductive Online Learning ⬇️

artículo científico publicado en 2006

Identifiability and Unmixing of Latent Parse Trees ⬇️

artículo científico publicado en 2012

Information Theoretic Regret Bounds for Online Nonlinear Control ⬇️

artículo científico publicado en 2020

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

Is Long Horizon RL More Difficult Than Short Horizon RL? ⬇️

scholarly article by Ruosong Wang et al published November 2020 in Advances in Neural Information Processing Systems 33

Learning Mixtures of Tree Graphical Models ⬇️

Learning Overcomplete HMMs ⬇️

artículo científico publicado en 2017

Learning from Logged Implicit Exploration Data ⬇️

Meta-Learning with Implicit Gradients ⬇️

Mind the Duality Gap: Logarithmic regret algorithms for online optimization ⬇️

scholarly article by Shai Shalev-shwartz & Sham M. Kakade published 2009 in Advances in Neural Information Processing Systems 21

Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity ⬇️

artículo científico publicado en 2020

Multi-Label Prediction via Compressed Sensing ⬇️

artículo científico publicado en 2009

Multi-view clustering via canonical correlation analysis

scientific article published on 16 June 2009

On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization ⬇️

On the Generalization Ability of Online Strongly Convex Programming Algorithms ⬇️

scholarly article by Sham M. Kakade & Ambuj Tewari published 2009 in Advances in Neural Information Processing Systems 21

Online Bounds for Bayesian Algorithms ⬇️

artículo científico publicado en 2005

Opponent interactions between serotonin and dopamine

artículo científico publicado en 2002

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning ⬇️

artículo científico publicado en 2020

Policy Search by Dynamic Programming ⬇️

artículo científico publicado en 2004

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent ⬇️

artículo científico publicado en 2016

Provably Correct Automatic Sub-Differentiation for Qualified Programs ⬇️

Robust Meta-learning for Mixed Linear Regression with Small Batches ⬇️

artículo científico publicado en 2020

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs ⬇️

scholarly article by Chi Jin et al published November 2020 in Advances in Neural Information Processing Systems 33

Spectral Methods for Learning Multivariate Latent Tree Structure ⬇️

artículo científico publicado en 2011

Stochastic convex optimization with bandit feedback ⬇️

artículo científico publicado en 2011

Super-Resolution Off the Grid ⬇️

Tensor Decompositions for Learning Latent Variable Models

The Price of Bandit Information for Online Optimization ⬇️

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares ⬇️

artículo científico publicado en 2019

Towards Generalization and Simplicity in Continuous Control ⬇️

artículo científico publicado en 2017

When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity ⬇️

Worst-Case Bounds for Gaussian Process Models ⬇️

artículo científico publicado en 2006

Lista de obras de Sham Kakade

A Natural Policy Gradient ⬇️

A Smoother Way to Train Structured Prediction Models ⬇️

A Spectral Algorithm for Latent Dirichlet Allocation ⬇️

A spectral algorithm for learning Hidden Markov Models

A tail inequality for quadratic forms of subgaussian random vectors ⬇️

Acquisition and extinction in autoshaping

Acquisition in Autoshaping ⬇️

Convergence Rates of Active Learning for Maximum Likelihood Estimation ⬇️

Dopamine Bonuses ⬇️

Dopamine: generalization and bonuses

Economic Properties of Social Networks ⬇️

Efficient Learning of Generalized Linear and Single Index Models with Isotonic Regression ⬇️

Experts in a Markov Decision Process ⬇️

Explaining Away in Weight Space ⬇️

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs ⬇️

From Batch to Transductive Online Learning ⬇️

Identifiability and Unmixing of Latent Parse Trees ⬇️

Information Theoretic Regret Bounds for Online Nonlinear Control ⬇️

Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting

Is Long Horizon RL More Difficult Than Short Horizon RL? ⬇️

Learning Mixtures of Tree Graphical Models ⬇️

Learning Overcomplete HMMs ⬇️

Learning from Logged Implicit Exploration Data ⬇️

Meta-Learning with Implicit Gradients ⬇️

Mind the Duality Gap: Logarithmic regret algorithms for online optimization ⬇️

Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity ⬇️

Multi-Label Prediction via Compressed Sensing ⬇️

Multi-view clustering via canonical correlation analysis

On the Complexity of Linear Prediction: Risk Bounds, Margin Bounds, and Regularization ⬇️

On the Generalization Ability of Online Strongly Convex Programming Algorithms ⬇️

Online Bounds for Bayesian Algorithms ⬇️

Opponent interactions between serotonin and dopamine

PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning ⬇️

Policy Search by Dynamic Programming ⬇️

Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent ⬇️

Provably Correct Automatic Sub-Differentiation for Qualified Programs ⬇️

Robust Meta-learning for Mixed Linear Regression with Small Batches ⬇️

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs ⬇️

Spectral Methods for Learning Multivariate Latent Tree Structure ⬇️

Stochastic convex optimization with bandit feedback ⬇️

Super-Resolution Off the Grid ⬇️

Tensor Decompositions for Learning Latent Variable Models

The Price of Bandit Information for Online Optimization ⬇️

The Step Decay Schedule: A Near Optimal, Geometrically Decaying Learning Rate Procedure For Least Squares ⬇️

Towards Generalization and Simplicity in Continuous Control ⬇️

When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity ⬇️

Worst-Case Bounds for Gaussian Process Models ⬇️