16 citations · 88 across the 24 of their papers we have counts for
20 papers · 1 filter
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Ziniu Li, Congliang Chen, Tianyun Yang +5
Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to explore and discover better solutions. However, this exploration p…
Exploring the Generalization Capabilities of AID-based Bi-level Optimization
Congliang Chen, Li Shen, Zhiqiang Xu +3
Bi-level optimization has achieved considerable success in contemporary machine learning applications, especially for given proper hyperparameters. However, due to the two-level op…
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
Ziniu Li, Congliang Chen, Tian Xu +4
Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However,…
Adam-mini: Use Fewer Learning Rates To Gain More
Yushun Zhang, Congliang Chen, Ziniu Li +6
We propose Adam-mini, an optimizer that achieves on par or better performance than AdamW with 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate…
Uniformly Stable Algorithms for Adversarial Training and Beyond
Jiancong Xiao, Jiawei Zhang, Zhi-Quan Luo +1
In adversarial machine learning, neural networks suffer from a significant issue known as robust overfitting, where the robust test accuracy decreases over epochs (Rice et al., 202…
Why Transformers Need Adam: A Hessian Perspective
Yushun Zhang, Congliang Chen, Tian Ding +3
SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear. In this work, we provide an explanation through the lens of Hessian: (i) Trans…
PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization
Jiancong Xiao, Ruoyu Sun, Zhi- Quan Luo
Deep neural networks (DNNs) are vulnerable to adversarial attacks. It is found empirically that adversarially robust generalization is crucial in establishing defense algorithms ag…
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
Ziniu Li, Tian Xu, Yushun Zhang +4
Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO…
A Distribution Optimization Framework for Confidence Bounds of Risk Measures
Hao Liang, Zhi-quan Luo
We present a distribution optimization framework that significantly improves confidence bounds for various risk measures compared to previous methods. Our framework encompasses pop…
Provably Efficient Adversarial Imitation Learning with Unknown Transitions
Tian Xu, Ziniu Li, Yang Yu +1
Imitation learning (IL) has proven to be an effective method for learning good policies from expert demonstrations. Adversarial imitation learning (AIL), a subset of IL methods, is…
Invariant Layers for Graphs with Nodes of Different Types
Dmitry Rybin, Ruoyu Sun, Zhi-Quan Luo
Neural networks that satisfy invariance with respect to input permutations have been widely studied in machine learning literature. However, in many applications, only a subset of…
Adversarial Rademacher Complexity of Deep Neural Networks
Jiancong Xiao, Yanbo Fan, Ruoyu Sun +1
Deep neural networks (DNNs) are highly vulnerable to adversarial attacks. Ideally, a robust model should perform well on both perturbed training data and unseen perturbed test data…
Stability Analysis and Generalization Bounds of Adversarial Training
Jiancong Xiao, Yanbo Fan, Ruoyu Sun +2
In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon…
Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis
Jiancong Xiao, Zeyu Qin, Yanbo Fan +3
Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of pertu…
Understanding Adversarial Robustness Against On-manifold Adversarial Examples
Jiancong Xiao, Liusha Yang, Yanbo Fan +2
Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One…
Provable Adaptivity of Adam under Non-uniform Smoothness
Bohan Wang, Yushun Zhang, Huishuai Zhang +6
Adam is widely adopted in practical applications due to its fast convergence. However, its theoretical analysis is still far from satisfactory. Existing convergence analyses for Ad…
Adam Can Converge Without Any Modification On Update Rules
Yushun Zhang, Congliang Chen, Naichen Shi +2
Ever since Reddi et al. 2018 pointed out the divergence issue of Adam, many new variants have been designed to obtain convergence. However, vanilla Adam remains exceptionally popul…
Understanding Adversarial Imitation Learning in Small Sample Regime: A Stage-coupled Analysis
Tian Xu, Ziniu Li, Yang Yu +1
Imitation learning learns a policy from expert trajectories. While the expert data is believed to be crucial for imitation quality, it was found that a kind of imitation learning a…
Rethinking ValueDice: Does It Really Improve Performance?
Ziniu Li, Tian Xu, Yang Yu +1
Since the introduction of GAIL, adversarial imitation learning (AIL) methods attract lots of research interests. Among these methods, ValueDice has achieved significant improvement…
On Generalization of Adversarial Imitation Learning and Beyond
Tian Xu, Ziniu Li, Yang Yu +1
Despite massive empirical evaluations, one of the fundamental questions in imitation learning is still not fully settled: does AIL (adversarial imitation learning) provably general…