8 citations · 39 across the 19 of their papers we have counts for
14 papers · 1 filter
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
Shuo Xie, Tianhao Wang, Sashank Reddi +2
We present a novel unified analysis for a broad class of adaptive optimization algorithms with structured (e.g., layerwise, diagonal, and kronecker-factored) preconditioners for bo…
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
Siyu Chen, Heejune Sheen, Tianhao Wang +1
In-context learning (ICL) is a cornerstone of large language model (LLM) functionality, yet its theoretical foundations remain elusive due to the complexity of transformer architec…
Implicit Regularization of Gradient Flow on One-Layer Softmax Attention
Heejune Sheen, Siyu Chen, Tianhao Wang +1
We study gradient flow on the exponential loss for a classification problem with a one-layer softmax attention model, where the key and query weight matrices are trained separately…
How Well Can Transformers Emulate In-context Newton's Method?
Angeliki Giannou, Liu Yang, Tianhao Wang +2
Transformer-based models have demonstrated remarkable in-context learning capabilities, prompting extensive research into its underlying mechanisms. Recent studies have suggested t…
Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality
Siyu Chen, Heejune Sheen, Tianhao Wang +1
We study the dynamics of gradient flow for training a multi-head softmax attention model for in-context learning of multi-task linear regression. We establish the global convergenc…
The Marginal Value of Momentum for Small Learning Rate SGD
Runzhe Wang, Sadhika Malladi, Tianhao Wang +2
Momentum is known to accelerate the convergence of gradient descent in strongly convex settings without stochastic gradient noise. In stochastic optimization, such as training neur…
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
Yifei Min, Jiafan He, Tianhao Wang +1
We study multi-agent reinforcement learning in the setting of episodic Markov decision processes, where multiple agents cooperate via communication through a central server. We pro…
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent
Zhiyuan Li, Tianhao Wang, JasonD. Lee +1
As part of the effort to understand implicit bias of gradient descent in overparametrized models, several results have shown how the training trajectory on the overparametrized mod…
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
Jiafan He, Tianhao Wang, Yifei Min +1
We study federated contextual linear bandits, where agents cooperate with each other to solve a global contextual linear bandit problem with the help of a central server. We co…
Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets
Yifei Min, Tianhao Wang, Ruitu Xu +3
We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market. At each step, the agents are presented with a dynamical context,…
Learning Stochastic Shortest Path with Linear Function Approximation
Yifei Min, Jiafan He, Tianhao Wang +1
We study the stochastic shortest path (SSP) problem in reinforcement learning with linear function approximation, where the transition kernel is represented as a linear mixture of…
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework
Zhiyuan Li, Tianhao Wang, Sanjeev Arora
Understanding the implicit bias of Stochastic Gradient Descent (SGD) is one of the key challenges in deep learning, especially for overparametrized models, where the local minimize…
Variance-Aware Off-Policy Evaluation with Linear Function Approximation
Yifei Min, Tianhao Wang, Dongruo Zhou +1
We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on…
Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints
Tianhao Wang, Dongruo Zhou, Quanquan Gu
We study reinforcement learning (RL) with linear function approximation under the adaptivity constraint. We consider two popular limited adaptivity models: the batch learning model…