Picture for Jason D. Lee

Jason D. Lee

Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity

Add code
Jun 28, 2024
Viaarxiv icon

Scaling Laws in Linear Regression: Compute, Parameters, and Data

Add code
Jun 12, 2024
Figure 1 for Scaling Laws in Linear Regression: Compute, Parameters, and Data
Figure 2 for Scaling Laws in Linear Regression: Compute, Parameters, and Data
Figure 3 for Scaling Laws in Linear Regression: Compute, Parameters, and Data
Figure 4 for Scaling Laws in Linear Regression: Compute, Parameters, and Data
Viaarxiv icon

Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot

Add code
Jun 11, 2024
Viaarxiv icon

Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit

Add code
Jun 03, 2024
Viaarxiv icon

REBEL: Reinforcement Learning via Regressing Relative Rewards

Add code
Apr 25, 2024
Figure 1 for REBEL: Reinforcement Learning via Regressing Relative Rewards
Figure 2 for REBEL: Reinforcement Learning via Regressing Relative Rewards
Figure 3 for REBEL: Reinforcement Learning via Regressing Relative Rewards
Figure 4 for REBEL: Reinforcement Learning via Regressing Relative Rewards
Viaarxiv icon

Dataset Reset Policy Optimization for RLHF

Add code
Apr 15, 2024
Figure 1 for Dataset Reset Policy Optimization for RLHF
Figure 2 for Dataset Reset Policy Optimization for RLHF
Figure 3 for Dataset Reset Policy Optimization for RLHF
Figure 4 for Dataset Reset Policy Optimization for RLHF
Viaarxiv icon

Horizon-Free Regret for Linear Markov Decision Processes

Add code
Mar 15, 2024
Viaarxiv icon

Computational-Statistical Gaps in Gaussian Single-Index Models

Add code
Mar 12, 2024
Figure 1 for Computational-Statistical Gaps in Gaussian Single-Index Models
Figure 2 for Computational-Statistical Gaps in Gaussian Single-Index Models
Figure 3 for Computational-Statistical Gaps in Gaussian Single-Index Models
Figure 4 for Computational-Statistical Gaps in Gaussian Single-Index Models
Viaarxiv icon

How Well Can Transformers Emulate In-context Newton's Method?

Add code
Mar 05, 2024
Figure 1 for How Well Can Transformers Emulate In-context Newton's Method?
Figure 2 for How Well Can Transformers Emulate In-context Newton's Method?
Figure 3 for How Well Can Transformers Emulate In-context Newton's Method?
Figure 4 for How Well Can Transformers Emulate In-context Newton's Method?
Viaarxiv icon

BitDelta: Your Fine-Tune May Only Be Worth One Bit

Add code
Feb 28, 2024
Viaarxiv icon