Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Sham Kakade

Sham Kakade

Gone Fishing: Neural Active Learning with Fisher Embeddings


Jun 17, 2021
Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Sham Kakade

Figure 1 for Gone Fishing: Neural Active Learning with Fisher Embeddings
Figure 2 for Gone Fishing: Neural Active Learning with Fisher Embeddings
Figure 3 for Gone Fishing: Neural Active Learning with Fisher Embeddings
Figure 4 for Gone Fishing: Neural Active Learning with Fisher Embeddings

  Access Paper or Ask Questions

LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes


Jun 02, 2021
Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan, Raghav Somani, Jae Sung Park, Krishna Pillutla, Prateek Jain, Sham Kakade, Ali Farhadi

Figure 1 for LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
Figure 2 for LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
Figure 3 for LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
Figure 4 for LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
* 18 pages, 6 figures 
  Access Paper or Ask Questions

Robust and Differentially Private Mean Estimation


Feb 18, 2021
Xiyang Liu, Weihao Kong, Sham Kakade, Sewoong Oh

Figure 1 for Robust and Differentially Private Mean Estimation
Figure 2 for Robust and Differentially Private Mean Estimation
Figure 3 for Robust and Differentially Private Mean Estimation
* 55 pages, 1 figure 
  Access Paper or Ask Questions

How Important is the Train-Validation Split in Meta-Learning?


Oct 12, 2020
Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong

Figure 1 for How Important is the Train-Validation Split in Meta-Learning?
Figure 2 for How Important is the Train-Validation Split in Meta-Learning?
Figure 3 for How Important is the Train-Validation Split in Meta-Learning?

  Access Paper or Ask Questions

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


Aug 13, 2020
Alekh Agarwal, Mikael Henaff, Sham Kakade, Wen Sun

Figure 1 for PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Figure 2 for PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Figure 3 for PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning
Figure 4 for PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning

  Access Paper or Ask Questions

Information Theoretic Regret Bounds for Online Nonlinear Control


Jun 22, 2020
Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun

Figure 1 for Information Theoretic Regret Bounds for Online Nonlinear Control
Figure 2 for Information Theoretic Regret Bounds for Online Nonlinear Control
Figure 3 for Information Theoretic Regret Bounds for Online Nonlinear Control

  Access Paper or Ask Questions

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs


Jun 18, 2020
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun

Figure 1 for FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Figure 2 for FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Figure 3 for FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

  Access Paper or Ask Questions

Robust Meta-learning for Mixed Linear Regression with Small Batches


Jun 18, 2020
Weihao Kong, Raghav Somani, Sham Kakade, Sewoong Oh

Figure 1 for Robust Meta-learning for Mixed Linear Regression with Small Batches
Figure 2 for Robust Meta-learning for Mixed Linear Regression with Small Batches
* 52 pages, 2 figures 
  Access Paper or Ask Questions

Soft Threshold Weight Reparameterization for Learnable Sparsity


Mar 11, 2020
Aditya Kusupati, Vivek Ramanujan, Raghav Somani, Mitchell Wortsman, Prateek Jain, Sham Kakade, Ali Farhadi

Figure 1 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Figure 2 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Figure 3 for Soft Threshold Weight Reparameterization for Learnable Sparsity
Figure 4 for Soft Threshold Weight Reparameterization for Learnable Sparsity
* 17 pages, 9 figures 
  Access Paper or Ask Questions

Optimal Regularization Can Mitigate Double Descent


Mar 04, 2020
Preetum Nakkiran, Prayaag Venkat, Sham Kakade, Tengyu Ma

Figure 1 for Optimal Regularization Can Mitigate Double Descent
Figure 2 for Optimal Regularization Can Mitigate Double Descent
Figure 3 for Optimal Regularization Can Mitigate Double Descent
Figure 4 for Optimal Regularization Can Mitigate Double Descent

  Access Paper or Ask Questions

The Implicit and Explicit Regularization Effects of Dropout


Mar 02, 2020
Colin Wei, Sham Kakade, Tengyu Ma

Figure 1 for The Implicit and Explicit Regularization Effects of Dropout
Figure 2 for The Implicit and Explicit Regularization Effects of Dropout
Figure 3 for The Implicit and Explicit Regularization Effects of Dropout
Figure 4 for The Implicit and Explicit Regularization Effects of Dropout

  Access Paper or Ask Questions

Provable Representation Learning for Imitation Learning via Bi-level Optimization


Feb 24, 2020
Sanjeev Arora, Simon S. Du, Sham Kakade, Yuping Luo, Nikunj Saunshi

Figure 1 for Provable Representation Learning for Imitation Learning via Bi-level Optimization
Figure 2 for Provable Representation Learning for Imitation Learning via Bi-level Optimization
Figure 3 for Provable Representation Learning for Imitation Learning via Bi-level Optimization
* 26 pages 
  Access Paper or Ask Questions

Meta-learning for mixed linear regression


Feb 20, 2020
Weihao Kong, Raghav Somani, Zhao Song, Sham Kakade, Sewoong Oh

Figure 1 for Meta-learning for mixed linear regression
Figure 2 for Meta-learning for mixed linear regression
Figure 3 for Meta-learning for mixed linear regression
Figure 4 for Meta-learning for mixed linear regression

  Access Paper or Ask Questions

Meta-Learning with Implicit Gradients


Sep 10, 2019
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine

Figure 1 for Meta-Learning with Implicit Gradients
Figure 2 for Meta-Learning with Implicit Gradients
Figure 3 for Meta-Learning with Implicit Gradients
Figure 4 for Meta-Learning with Implicit Gradients
* NeurIPS 2019. First two authors contributed equally 
  Access Paper or Ask Questions

On the Optimality of Sparse Model-Based Planning for Markov Decision Processes


Jul 04, 2019
Alekh Agarwal, Sham Kakade, Lin F. Yang

Figure 1 for On the Optimality of Sparse Model-Based Planning for Markov Decision Processes

  Access Paper or Ask Questions

Online Meta-Learning


Feb 22, 2019
Chelsea Finn, Aravind Rajeswaran, Sham Kakade, Sergey Levine

Figure 1 for Online Meta-Learning
Figure 2 for Online Meta-Learning
Figure 3 for Online Meta-Learning
Figure 4 for Online Meta-Learning
* The first two authors contributed equally 
  Access Paper or Ask Questions

Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control


Jan 28, 2019
Kendall Lowrey, Aravind Rajeswaran, Sham Kakade, Emanuel Todorov, Igor Mordatch

Figure 1 for Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Figure 2 for Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Figure 3 for Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
Figure 4 for Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
* The first two authors contributed equally. Accepted at ICLR 2019. Supplementary videos available at: https://sites.google.com/view/polo-mpc 
  Access Paper or Ask Questions

Provably Correct Automatic Subdifferentiation for Qualified Programs


Sep 23, 2018
Sham Kakade, Jason D. Lee

Figure 1 for Provably Correct Automatic Subdifferentiation for Qualified Programs

  Access Paper or Ask Questions

Variance Reduction Methods for Sublinear Reinforcement Learning


Aug 25, 2018
Sham Kakade, Mengdi Wang, Lin F. Yang

Figure 1 for Variance Reduction Methods for Sublinear Reinforcement Learning
* Fixed a bug of a previous version 
  Access Paper or Ask Questions

Prediction with a Short Memory


Jun 28, 2018
Vatsal Sharan, Sham Kakade, Percy Liang, Gregory Valiant

Figure 1 for Prediction with a Short Memory
* Updates for STOC camera ready 
  Access Paper or Ask Questions

Learning Overcomplete HMMs


Jun 28, 2018
Vatsal Sharan, Sham Kakade, Percy Liang, Gregory Valiant

Figure 1 for Learning Overcomplete HMMs
Figure 2 for Learning Overcomplete HMMs
Figure 3 for Learning Overcomplete HMMs
Figure 4 for Learning Overcomplete HMMs
* Added acknowledgements 
  Access Paper or Ask Questions

Stochastic subgradient method converges on tame functions


May 26, 2018
Damek Davis, Dmitriy Drusvyatskiy, Sham Kakade, Jason D. Lee

Figure 1 for Stochastic subgradient method converges on tame functions
* 32 pages, 1 figure 
  Access Paper or Ask Questions