Related papers: Adaptive Low-Rank Regularization with Damping Sequ…

Reinforcement learning (RL) is a key post-pretraining step for aligning large language models (LLMs) with complex tasks and human preferences. While it is often assumed that RL fine-tuning requires updating most of a model's parameters, we…

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

Stochastic optimization plays a crucial role in the advancement of deep learning technologies. Over the decades, significant effort has been dedicated to improving the training efficiency and robustness of deep neural networks, via various…

Low Rank Decomposition (LRD) is a model compression technique applied to the weight tensors of deep learning models in order to reduce the number of trainable parameters and computational complexity. However, due to high number of new…

Deep reinforcement learning algorithms that learn policies by trial-and-error must learn from limited amounts of data collected by actively interacting with the environment. While many prior works have shown that proper regularization…

Modern deep neural networks are highly over-parameterized compared to the data on which they are trained, yet they often generalize remarkably well. A flurry of recent work has asked: why do deep networks not overfit to their training data?…

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method validated across NLP and CV domains. However, LoRA faces an inherent low-rank bottleneck: narrowing its performance gap with full finetuning…

Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniques are increasingly important. One of the most widely used…

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible…

The Aircraft Landing Problem (ALP) is one of the challenging problems in aircraft transportation and management. The challenge is to schedule the arriving aircraft in a sequence so that the cost and delays are optimized. There are various…

Last-layer retraining (LLR) methods -- wherein the last layer of a neural network is reinitialized and retrained on a held-out set following ERM training -- have garnered interest as an efficient approach to rectify dependence on spurious…

Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfitting, i.e., the robustness starts to decrease significantly…

Despite overparameterization, deep networks trained via supervised learning are easy to optimize and exhibit excellent generalization. One hypothesis to explain this is that overparameterized deep networks enjoy the benefits of implicit…

Neural growth is the process of growing a small neural network to a large network and has been utilized to accelerate the training of deep neural networks. One crucial aspect of neural growth is determining the optimal growth timing.…

Mixup is a recent regularizer for current deep classification networks. Through training a neural network on convex combinations of pairs of examples and their labels, it imposes locally linear constraints on the model's input space.…

Over-parametrization is an important technique in training neural networks. In both theory and practice, training a larger network allows the optimization algorithm to avoid bad local optimal solutions. In this paper we study a closely…

While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source…

The past decade has seen the rapid development of Reinforcement Learning, which acquires impressive performance with numerous training resources. However, one of the greatest challenges in RL is generalization efficiency (i.e.,…

In recent years, great progress has been made in a variety of application domains thanks to the development of increasingly deeper neural networks. Unfortunately, the huge number of units of these networks makes them expensive both…

Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has…