1 code implementation • 19 Apr 2024 • Yukang Wei, Yu Bai
Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD).
2 code implementations • 16 Apr 2024 • Yu-Yang Li, Yu Bai, Cunshi Wang, Mengwei Qu, Ziteng Lu, Roberto Soria, Jifeng Liu
Light curves serve as a valuable source of information on stellar formation and evolution.
no code implementations • 8 Apr 2024 • Ruiqi Zhang, Licong Lin, Yu Bai, Song Mei
LLM unlearning aims to eliminate the influence of undesirable data from the pre-trained model while preserving the model's utilities on other tasks.
no code implementations • 20 Jan 2024 • Yu Bai, Heyan Huang, Cesare Spinoso-Di Piano, Marc-Antoine Rondeau, Sanxing Chen, Yang Gao, Jackie Chi Kit Cheung
In-context learning (ICL) has become an effective solution for few-shot learning in natural language processing.
no code implementations • 29 Nov 2023 • Lei Zhao, Mengdi Wang, Yu Bai
Inverse Reinforcement Learning (IRL) -- the problem of learning reward functions from demonstrations of an \emph{expert policy} -- plays a critical role in developing intelligent systems.
no code implementations • 16 Oct 2023 • Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai
Through extensive probing and a new pasting experiment, we further reveal several mechanisms within the trained transformers, such as concrete copying behaviors on both the inputs and the representations, linear ICL capability of the upper layers alone, and a post-ICL representation selection mechanism in a harder mixture setting.
1 code implementation • 12 Oct 2023 • Licong Lin, Yu Bai, Song Mei
This provides the first quantitative analysis of the ICRL capabilities of transformers pretrained from offline trajectories.
no code implementations • 11 Sep 2023 • Yukai Miao, Yu Bai, Li Chen, Dan Li, Haifeng Sun, Xizheng Wang, Ziqiu Luo, Yanyu Ren, Dapeng Sun, Xiuting Xu, Qi Zhang, Chao Xiang, Xinchi Li
Nowadays, the versatile capabilities of Pre-trained Large Language Models (LLMs) have attracted much attention from the industry.
no code implementations • 6 Jul 2023 • Jiacheng Guo, Minshuo Chen, Huan Wang, Caiming Xiong, Mengdi Wang, Yu Bai
This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case.
no code implementations • 29 Jun 2023 • Simone Wills, Yu Bai, Cristian Tejedor-Garcia, Catia Cucchiarini, Helmer Strik
Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning.
no code implementations • 7 Jun 2023 • Yu Bai, Cristian Tejedor-Garcia, Ferdy Hubers, Catia Cucchiarini, Helmer Strik
We saw that ASR has potential at this stage of the reading process, as the results suggested that pupils made progress in reading accuracy and fluency by using the software.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 2 Jun 2023 • Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, Mengdi Wang
We present algorithms and establish near-optimal regret upper and lower bounds, of the form $\tilde{\mathcal{O}}(\sqrt{{\rm poly}(H) SAK})$, for RL in the delayed and missing observation settings.
2 code implementations • 15 Feb 2023 • Aadyot Bhatnagar, Huan Wang, Caiming Xiong, Yu Bai
We prove that our methods achieve near-optimal strongly adaptive regret for all interval lengths simultaneously, and approximately valid coverage.
no code implementations • 13 Feb 2023 • Yuanhao Wang, Qinghua Liu, Yu Bai, Chi Jin
A unique challenge in Multi-Agent Reinforcement Learning (MARL) is the curse of multiagency, where the description length of the game as well as the complexity of many existing learning algorithms scale exponentially with the number of agents.
no code implementations • 6 Feb 2023 • Yuheng Zhang, Yu Bai, Nan Jiang
We study offline multi-agent reinforcement learning (RL) in Markov games, where the goal is to learn an approximate equilibrium -- such as Nash equilibrium and (Coarse) Correlated Equilibrium -- from an offline dataset pre-collected from the game.
Multi-agent Reinforcement Learning Reinforcement Learning (RL)
no code implementations • 2 Feb 2023 • Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai
However, the fundamental limits for learning in revealing POMDPs are much less understood, with existing lower bounds being rather preliminary and having substantial gaps from the current best upper bounds.
no code implementations • 23 Oct 2022 • Prafulla Kumar Choubey, Yu Bai, Chien-Sheng Wu, Wenhao Liu, Nazneen Rajani
Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification.
no code implementations • 20 Oct 2022 • Yuanhao Wang, Dingwen Kong, Yu Bai, Chi Jin
This paper develops the first line of efficient algorithms for learning rationalizable Coarse Correlated Equilibria (CCE) and Correlated Equilibria (CE) whose sample complexities are polynomial in all problem parameters including the number of players.
no code implementations • 9 Oct 2022 • Tengyang Xie, Dylan J. Foster, Yu Bai, Nan Jiang, Sham M. Kakade
Coverage conditions -- which assert that the data logging distribution adequately covers the state space -- play a fundamental role in determining the sample complexity of offline reinforcement learning.
no code implementations • 29 Sep 2022 • Fan Chen, Yu Bai, Song Mei
Recent work has identified several tractable subclasses that are learnable with polynomial samples, such as Partially Observable Markov Decision Processes (POMDPs) with certain revealing or decodability conditions.
no code implementations • 23 Sep 2022 • Fan Chen, Song Mei, Yu Bai
We make progress on this question by developing a unified algorithm framework for a large class of learning goals, building on the Decision-Estimation Coefficient (DEC) framework.
1 code implementation • 8 Jun 2022 • Eshaan Nichani, Yu Bai, Jason D. Lee
Next, we show that a wide two-layer neural network can jointly use the NTK and QuadNTK to fit target functions consisting of a dense low-degree term and a sparse high-degree term -- something neither the NTK nor the QuadNTK can do on their own.
no code implementations • 6 Jun 2022 • Runyu Zhang, Qinghua Liu, Huan Wang, Caiming Xiong, Na Li, Yu Bai
Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate.
no code implementations • 30 May 2022 • Yu Bai, Chi Jin, Song Mei, Ziang Song, Tiancheng Yu
A conceptually appealing approach for learning Extensive-Form Games (EFGs) is to convert them to Normal-Form Games (NFGs).
no code implementations • 15 May 2022 • Ziang Song, Song Mei, Yu Bai
We then design an uncoupled no-regret algorithm that finds an $\varepsilon$-approximate $K$-EFCE within $\widetilde{\mathcal{O}}(\max_{i}X_iA_i^{K}/\varepsilon^2)$ iterations in the full feedback setting, where $X_i$ and $A_i$ are the number of information sets and actions for the $i$-th player.
no code implementations • COLING 2022 • Xiaochen Liu, Yang Gao, Yu Bai, Jiawei Li, Yinan Hu, Heyan Huang, Boxing Chen
Few-shot abstractive summarization has become a challenging task in natural language generation.
1 code implementation • 30 Mar 2022 • Jiaao Zhan, Qian Chen, Boxing Chen, Wen Wang, Yu Bai, Yang Gao
We propose a novel and general Dependency-Aware Decoder (DePA) to enhance target dependency modeling in the decoder of fully NAT models from two perspectives: decoder self-attention and decoder input.
1 code implementation • ICLR 2022 • Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong
Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly over existing approaches in several applications such as prediction intervals with improved length, minimum-volume prediction sets for multi-output regression, and label prediction sets for image classification.
no code implementations • 13 Feb 2022 • Hao Wang, Yu Bai, Guangmin Sun, Jie Liu
Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy.
no code implementations • 3 Feb 2022 • Yu Bai, Chi Jin, Song Mei, Tiancheng Yu
This improves upon the best known sample complexity of $\widetilde{\mathcal{O}}((X^2A+Y^2B)/\varepsilon^2)$ by a factor of $\widetilde{\mathcal{O}}(\max\{X, Y\})$, and matches the information-theoretic lower bound up to logarithmic factors.
no code implementations • 3 Jan 2022 • Michael Curry, Alexander Trott, Soham Phade, Yu Bai, Stephan Zheng
We validate the learned solutions are $\epsilon$-meta-equilibria through best-response analyses, show that they align with economic intuitions, and show our approach can learn a spectrum of qualitatively distinct $\epsilon$-meta-equilibria in open RBC models.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 15 Oct 2021 • Yu Bai, Heyan Huang, Kai Fan, Yang Gao, Yiming Zhu, Jiaao Zhan, Zewen Chi, Boxing Chen
Through introducing compression rate, the information ratio between the source and the target text, we regard the MT task as a special CLS task with a compression rate of 100%.
no code implementations • ICLR 2022 • Ziang Song, Song Mei, Yu Bai
First, we design algorithms for learning an $\epsilon$-Coarse Correlated Equilibrium (CCE) in $\widetilde{\mathcal{O}}(H^5S\max_{i\le m} A_i / \epsilon^2)$ episodes, and an $\epsilon$-Correlated Equilibrium (CE) in $\widetilde{\mathcal{O}}(H^6S\max_{i\le m} A_i^2 / \epsilon^2)$ episodes.
no code implementations • 23 Sep 2021 • Zewen Chi, Heyan Huang, Luyang Liu, Yu Bai, Xian-Ling Mao
The success of pretrained cross-lingual language models relies on two essential abilities, i. e., generalization ability for learning downstream tasks in a source language, and cross-lingual transferability for transferring the task knowledge to other languages.
no code implementations • NeurIPS 2021 • Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Estimating the data uncertainty in regression tasks is often done by learning a quantile function or a prediction interval of the true label conditioned on the input.
no code implementations • NeurIPS 2021 • Tengyang Xie, Nan Jiang, Huan Wang, Caiming Xiong, Yu Bai
This offline result is the first that matches the sample complexity lower bound in this setting, and resolves a recent open question in offline RL.
1 code implementation • ACL 2021 • Yu Bai, Yang Gao, Heyan Huang
Employing one unified decoder to generate the sequential concatenation of monolingual and cross-lingual summaries, MCLAS makes the monolingual summarization task a prerequisite of the cross-lingual summarization (CLS) task.
Abstractive Text Summarization Cross-Lingual Abstractive Summarization +2
no code implementations • 30 Mar 2021 • Bo Dong, Hao liu, Yu Bai, Jinbiao Lin, Zhuoran Xu, Xinyu Xu, Qi Kong
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety.
no code implementations • 8 Mar 2021 • Zitong Yang, Yu Bai, Song Mei
We show that, in the setting where the classical uniform convergence bound is vacuous (diverges to $\infty$), uniform convergence over the interpolators still gives a non-trivial bound of the test error of interpolating solutions.
no code implementations • NeurIPS 2021 • Yu Bai, Chi Jin, Huan Wang, Caiming Xiong
Real world applications such as economics and policy making often involve solving multi-agent games with two unique features: (1) The agents are inherently asymmetric and partitioned into leaders and followers; (2) The agents have different reward functions, thus the game is general-sum.
no code implementations • 22 Feb 2021 • Rachel Luo, Aadyot Bhatnagar, Yu Bai, Shengjia Zhao, Huan Wang, Caiming Xiong, Silvio Savarese, Stefano Ermon, Edward Schmerling, Marco Pavone
In this work, we propose the local calibration error (LCE) to span the gap between average and individual reliability.
no code implementations • 15 Feb 2021 • Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Modern machine learning models with high accuracy are often miscalibrated -- the predicted top probability does not reflect the actual accuracy, and tends to be over-confident.
no code implementations • NeurIPS 2021 • Ming Yin, Yu Bai, Yu-Xiang Wang
Our main result shows that OPDVR provably identifies an $\epsilon$-optimal policy with $\widetilde{O}(H^2/d_m\epsilon^2)$ episodes of offline data in the finite-horizon stationary transition setting, where $H$ is the horizon length and $d_m$ is the minimal marginal state-action distribution induced by the behavior policy.
no code implementations • 1 Jan 2021 • Yu Bai, Tengyu Ma, Huan Wang, Caiming Xiong
In this paper, we propose Neural Rank Preserving Transforms (NRPT), a new post-calibration method that adjusts the output probabilities of a trained classifier using a calibrator of higher capacity, while maintaining its prediction accuracy.
no code implementations • 12 Oct 2020 • Yu Bai, Minshuo Chen, Pan Zhou, Tuo Zhao, Jason D. Lee, Sham Kakade, Huan Wang, Caiming Xiong
A common practice in meta-learning is to perform a train-validation split (\emph{train-val method}) where the prior adapts to the task on one split of the data, and the resulting predictor is evaluated on another split.
no code implementations • 4 Oct 2020 • Qinghua Liu, Tiancheng Yu, Yu Bai, Chi Jin
However, for multi-agent reinforcement learning in Markov games, the current best known sample complexity for model-based algorithms is rather suboptimal and compares unfavorably against recent model-free approaches.
Model-based Reinforcement Learning Multi-agent Reinforcement Learning +2
no code implementations • 7 Jul 2020 • Ming Yin, Yu Bai, Yu-Xiang Wang
The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications.
no code implementations • NeurIPS 2020 • Minshuo Chen, Yu Bai, Jason D. Lee, Tuo Zhao, Huan Wang, Caiming Xiong, Richard Socher
When the trainable network is the quadratic Taylor model of a wide two-layer network, we show that neural representation can achieve improved sample complexities compared with the raw input: For learning a low-rank degree-$p$ polynomial ($p \geq 4$) in $d$ dimension, neural representation requires only $\tilde{O}(d^{\lceil p/2 \rceil})$ samples, while the best-known sample complexity upper bound for the raw input is $\tilde{O}(d^{p-1})$.
no code implementations • NeurIPS 2020 • Yu Bai, Chi Jin, Tiancheng Yu
This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games.
no code implementations • ICML 2020 • Yu Bai, Chi Jin
We introduce a self-play algorithm---Value Iteration with Upper/Lower Confidence Bound (VI-ULCB)---and show that it achieves regret $\tilde{\mathcal{O}}(\sqrt{T})$ after playing $T$ steps of the game, where the regret is measured by the agent's performance against a \emph{fully adversarial} opponent who can exploit the agent's strategy at \emph{any} step.
no code implementations • 10 Feb 2020 • Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width.
no code implementations • 21 Oct 2019 • Ke Zhan, Shimiao Jiang, Yu Bai, Yi Li, Xu Liu, Zhuoran Xu
Eltwise layer is a commonly used structure in the multi-branch deep learning network.
no code implementations • ICLR 2020 • Yu Bai, Jason D. Lee
Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs).
no code implementations • NeurIPS 2019 • Yu Bai, Tengyang Xie, Nan Jiang, Yu-Xiang Wang
We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is, algorithms that change its exploration policy as infrequently as possible during regret minimization.
no code implementations • 1 Mar 2019 • Yu Bai, John Duchi, Song Mei
We study a family of (potentially non-convex) constrained optimization problems with convex composite structure.
1 code implementation • ICLR 2019 • Yu Bai, Qijia Jiang, Ju Sun
This paper concerns dictionary learning, i. e., sparse coding, a fundamental representation learning problem.
1 code implementation • ICLR 2019 • Yu Bai, Yu-Xiang Wang, Edo Liberty
To make deep neural networks feasible in resource-constrained environments (such as mobile devices), it is beneficial to quantize models by using low-precision weights.
no code implementations • ICLR 2019 • Yu Bai, Tengyu Ma, Andrej Risteski
Our preliminary experiments show that on synthetic datasets the test IPM is well correlated with KL divergence or the Wasserstein distance, indicating that the lack of diversity in GANs may be caused by the sub-optimality in optimization instead of statistical inefficiency.
no code implementations • 29 Aug 2017 • Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yi-Peng Zhang, Jian Tang, Qinru Qiu, Xue Lin, Bo Yuan
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
no code implementations • 10 Jul 2017 • Yu Bai, Sally Goldman, Li Zhang
TAPAS is a novel adaptive sampling method for the softmax model.
no code implementations • 22 Jul 2016 • Song Mei, Yu Bai, Andrea Montanari
We establish uniform convergence of the gradient and Hessian of the empirical risk to their population counterparts, as soon as the number of samples becomes larger than the number of unknown parameters (modulo logarithmic factors).