12 accepted papers
For RL algorithms, appropriate entropy control is crucial to their effectiveness. To control the policy entropy, a commonly used method is entropy regularization, which is adopted in various popular RL algorithms including PPO, SAC and A3C. Although entropy regularization proves effective in robotic…
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper network layers. To address this, we propose REVIS, a training-…
Fine-tuning on task-specific data to boost downstream performance is a crucial step for leveraging Large Language Models (LLMs). However, though fine-tuning enhances the model performance for specialized applications, previous studies have demonstrated that fine-tuning the models on several adversar…
Gradient-based bilevel optimization methods have been applied to a wide range of applications including hyper-parameter optimization, meta-learning, and model pruning. However, it is known that the bilevel optimization problem is difficult to solve, and the finite-time guarantee has only been establ…
In this paper, we present a novel bilevel optimization-based training approach to training acoustic models for automatic speech recognition (ASR) tasks that we term bi-level joint unsupervised and supervised training (BL-JUST). BL-JUST employs a lower and upper level optimization with an unsupervise…
Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But bilevel problems such as incentive design, inverse reinforce…
Bilevel optimization, which captures the inherent nested structure of machine learning problems, is gaining popularity in many recent applications. Existing works on bilevel optimization mostly consider either the unconstrained problems or the constrained upper-level problems. In this context, this…
Federated learning (FL) has received increasing interests during the past years, However, most of the existing works focus on supervised learning, and federated learning for sequential decision making has not been fully explored. Part of the reason is that learning a policy for sequential decision m…
Many machine learning problems today have multiple objective functions. They appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimiz…
Bilevel optimization enjoys a wide range of applications in hyper-parameter optimization, meta-learning and reinforcement learning. However, bilevel problems are difficult to solve and recent progress on scalable bilevel algorithms mainly focuses on bilevel optimization problems where the lower-leve…
Stochastic approximation (SA) with multiple coupled sequences has found broad applications in machine learning such as bilevel learning and reinforcement learning (RL). In this paper, we study the finite-time convergence of nonlinear SA with multiple coupled sequences. Different from existing multi-…
This paper considers the policy evaluation problem in reinforcement learning with agents of a decentralized and directed network. The focus is on decentralized temporal-difference (TD) learning with linear function approximation in the presence of unreliable or even malicious agents, termed as Byzan…