Search Results for author:
Found 61 papers, 9 papers with code
Improved Online Conformal Prediction via Strongly Adaptive Online Learning
We prove that our methods achieve near-optimal strongly adaptive regret for all interval lengths simultaneously, and approximately valid coverage.
Cross-Lingual Abstractive Summarization with Limited Parallel Resources
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
+1
ProxQuant: Quantized Neural Networks via Proximal Operators
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.
Unifying Cross-lingual Summarization and Machine Translation with Compression Rate
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%.
Efficient and Differentiable Conformal Prediction with General Function Classes
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.
Subgradient Descent Learns Orthogonal Dictionaries
This paper concerns dictionary learning, i. e., sparse coding, a fundamental representation learning problem.
DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder
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.
Dynamic Temperature Knowledge Distillation
Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD).
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
TAPAS: Two-pass Approximate Adaptive Sampling for Softmax
TAPAS is a novel adaptive sampling method for the softmax model.
The Landscape of Empirical Risk for Non-convex Losses
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).
Approximability of Discriminators Implies Diversity in GANs
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.
Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs
We study a family of (potentially non-convex) constrained optimization problems with convex composite structure.
Provably Efficient Q-Learning with Low Switching Cost
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.
Beyond Linearization: On Quadratic and Higher-Order Approximation of Wide Neural Networks
Recent theoretical work has established connections between over-parametrized neural networks and linearized models governed by he Neural Tangent Kernels (NTKs).
Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning
Eltwise layer is a commonly used structure in the multi-branch deep learning network.
Provable Self-Play Algorithms for Competitive Reinforcement Learning
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.
Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width.
Near-Optimal Reinforcement Learning with Self-Play
This paper considers the problem of designing optimal algorithms for reinforcement learning in two-player zero-sum games.
Towards Understanding Hierarchical Learning: Benefits of Neural Representations
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 $\tilde{O}(d^{p-1})$.
Near-Optimal Provable Uniform Convergence in Offline Policy Evaluation for Reinforcement Learning
The problem of Offline Policy Evaluation (OPE) in Reinforcement Learning (RL) is a critical step towards applying RL in real-life applications.
Improved Uncertainty Post-Calibration via Rank Preserving Transforms
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.
A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
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
How Important is the Train-Validation Split in Meta-Learning?
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.
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction
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.
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification
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.
Local Calibration: Metrics and Recalibration
In this work, we propose the local calibration error (LCE) to span the gap between average and individual reliability.
Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games
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.
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models
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.
Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety.
Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning
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.
Understanding the Under-Coverage Bias in Uncertainty Estimation
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.
Cross-Lingual Language Model Meta-Pretraining
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.
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?
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.
Analyzing Micro-Founded General Equilibrium Models with Many Agents using Deep Reinforcement Learning
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
Near-Optimal Learning of Extensive-Form Games with Imperfect Information
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.
Privacy protection based on mask template
Powerful recognition algorithms are widely used in the Internet or important medical systems, which poses a serious threat to personal privacy.
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Few-shot abstractive summarization has become a challenging task in natural language generation.
Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games
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.
Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent
A conceptually appealing approach for learning Extensive-Form Games (EFGs) is to convert them to Normal-Form Games (NFGs).
Policy Optimization for Markov Games: Unified Framework and Faster Convergence
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.
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
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.
Unified Algorithms for RL with Decision-Estimation Coefficients: No-Regret, PAC, and Reward-Free Learning
Finding unified complexity measures and algorithms for sample-efficient learning is a central topic of research in reinforcement learning (RL).
Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms
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.
The Role of Coverage in Online Reinforcement Learning
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.
Learning Rationalizable Equilibria in Multiplayer Games
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.
Conformal Predictor for Improving Zero-shot Text Classification Efficiency
Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification.
Lower Bounds for Learning in Revealing POMDPs
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.
Offline Learning in Markov Games with General Function Approximation
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)
Breaking the Curse of Multiagency: Provably Efficient Decentralized Multi-Agent RL with Function Approximation
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.
Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations
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.
An ASR-Based Tutor for Learning to Read: How to Optimize Feedback to First Graders
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
Automatic Speech Recognition of Non-Native Child Speech for Language Learning Applications
Voicebots have provided a new avenue for supporting the development of language skills, particularly within the context of second language learning.
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
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.
An Empirical Study of NetOps Capability of Pre-Trained Large Language Models
Nowadays, the versatile capabilities of Pre-trained Large Language Models (LLMs) have attracted much attention from the industry.
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
This provides the first quantitative analysis of the ICRL capabilities of transformers pretrained from offline trajectories.
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
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.
Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective
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.
Identifying and Analyzing Task-Encoding Tokens in Large Language Models
In-context learning (ICL) has become an effective solution for few-shot learning in natural language processing.
Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
LLM unlearning aims to eliminate the influence of undesirable data from the pre-trained model while preserving the model's utilities on other tasks.
Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
Light curves serve as a valuable source of information on stellar formation and evolution.
