26 citations · 115 across the 68 of their papers we have counts for
9 papers · 1 filter
Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization
Ziqing Xu, Hancheng Min, Lachlan Ewen MacDonald +4
Despite the empirical success of Low-Rank Adaptation (LoRA) in fine-tuning pre-trained models, there is little theoretical understanding of how first-order methods with carefully c…
Learning safety critics via a non-contractive binary bellman operator
Agustin Castellano, Hancheng Min, Juan Andrés Bazerque +1
The inability to naturally enforce safety in Reinforcement Learning (RL), with limited failures, is a core challenge impeding its use in real-world applications. One notion of safe…
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
Hancheng Min, Enrique Mallada, René Vidal
This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with wel…
Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics
Tianqi Zheng, Pengcheng You, Enrique Mallada
In constrained reinforcement learning (C-RL), an agent seeks to learn from the environment a policy that maximizes the expected cumulative reward while satisfying minimum requireme…
Model-free Learning of Regions of Attraction via Recurrent Sets
Yue Shen, Maxim Bichuch, Enrique Mallada
We consider the problem of learning an inner approximation of the region of attraction (ROA) of an asymptotically stable equilibrium point without an explicit model of the dynamics…
Reinforcement Learning with Almost Sure Constraints
Agustin Castellano, Hancheng Min, Juan Bazerque +1
In this work we address the problem of finding feasible policies for Constrained Markov Decision Processes under probability one constraints. We argue that stationary policies are…
Convergence and Implicit Bias of Gradient Flow on Overparametrized Linear Networks
Hancheng Min, Salma Tarmoun, Rene Vidal +1
Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overpa…
Assured RL: Reinforcement Learning with Almost Sure Constraints
Agustin Castellano, Juan Bazerque, Enrique Mallada
We consider the problem of finding optimal policies for a Markov Decision Process with almost sure constraints on state transitions and action triplets. We define value and action-…
Learning to be safe, in finite time
Agustin Castellano, Juan Bazerque, Enrique Mallada
This paper aims to put forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an…