Enrique Mallada
9 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
๐ฃ Hot Topic Early Bird ๐ Conference Polyglot (4) ๐บ๏ธ Taxonomy Completionist (12) ๐งญ Keyword Pioneer ๐ Cross-Pollinator (5)
๐
Interdisciplinary Bridge
๐
Keyword Champion
(2)
๐ฅ
Unstoppable
(5)
Conferences
AISTATS (3)
ICML (3)
L4DC (2)
ICLR (1)
Top co-authors
Keywords
gradient descent
(2)
linear network
(2)
reinforcement learning
(1)
spectral clustering
(1)
graph laplacian
(1)
global convergence
(1)
policy learning
(1)
restricted isometry property
(1)
constrained markov decision process
(1)
convergence rate
(1)
weight initialization
(1)
gradient flow
(1)
implicit bia
(1)
model reduction
(1)
exponential convergence
(1)
stationary policy
(1)
dynamic network
(1)
subspace-preserving recovery
(1)
multi-layer linear model
(1)
gradient dominance property
(1)
Papers
Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits
AISTATS 2025
Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization
AISTATS 2025
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
ICLR 2024
Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization
AISTATS 2023
On the Convergence of Gradient Flow on Multi-layer Linear Models
ICML 2023
Learning Coherent Clusters in Weakly-Connected Network Systems
L4DC 2023
Reinforcement Learning with Almost Sure Constraints
L4DC 2022
A Nullspace Property for Subspace-Preserving Recovery
ICML 2021
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks
ICML 2021