15 citations · 22 across the 13 of their papers we have counts for
13 papers
A Local Polyak-Lojasiewicz and Descent Lemma of Gradient Descent For Overparametrized Linear Models
Ziqing Xu, Hancheng Min, Salma Tarmoun +2
Most prior work on the convergence of gradient descent (GD) for overparameterized neural networks relies on strong assumptions on the step size (infinitesimal), the hidden-layer wi…
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…
A Frequency Domain Analysis of Slow Coherency in Networked Systems
Hancheng Min, Richard Pates, Enrique Mallada
Network coherence generally refers to the emergence of simple aggregated dynamical behaviours, despite heterogeneity in the dynamics of the subsystems that constitute the network.…
Learning Coherent Clusters in Weakly-Connected Network Systems
Hancheng Min, Enrique Mallada
We propose a structure-preserving model-reduction methodology for large-scale dynamic networks with tightly-connected components. First, the coherent groups are identified by a spe…
Spectral clustering and model reduction for weakly-connected coherent network systems
Hancheng Min, Enrique Mallada
We propose a novel model-reduction methodology for large-scale dynamic networks with tightly-connected components. First, the coherent groups are identified by a spectral clusterin…
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…
Learning to Act Safely with Limited Exposure and Almost Sure Certainty
Agustin Castellano, Hancheng Min, Juan Bazerque +1
This paper puts 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 unboun…
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…
Coherence and Concentration in Tightly-Connected Networks
Hancheng Min, Richard Pates, Enrique Mallada
The ability to achieve coordinated behavior -- engineered or emergent -- on networked systems has attracted widespread interest over several fields. This interest has led to remark…
Accurate Reduced-Order Models for Heterogeneous Coherent Generators
Hancheng Min, Fernando Paganini, Enrique Mallada
We introduce a novel framework to approximate the aggregate frequency dynamics of coherent generators. By leveraging recent results on dynamics concentration of tightly connected n…
Dynamics Concentration of Large-Scale Tightly-Connected Networks
Hancheng Min, Enrique Mallada
The ability to achieve coordinated behavior --engineered or emergent-- on networked systems has attracted widespread interest over several fields. This has led to remarkable advanc…