collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Exact Convex Reformulations of Linear Neural Networks via Completely Positive Lifting

Karthik Prakhya, Alp Yurtsever

We show that the training problem of a deep linear neural network under the squared loss admits an exact convex reformulation in a lifted space over a generalized completely positi…

cs.LG2025

Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecture

Yikun Hou, Suvrit Sra, Alp Yurtsever

Gradient descent for matrix factorization exhibits an implicit bias toward approximately low-rank solutions. While existing theories often assume the boundedness of iterates, empir…

cs.LG2025

Provable Reduction in Communication Rounds for Non-Smooth Convex Federated Learning

Karlo Palenzuela, Ali Dadras, Alp Yurtsever +1

Multiple local steps are key to communication-efficient federated learning. However, theoretical guarantees for such algorithms, without data heterogeneity-bounding assumptions, ha…

cs.LG2025

Convex Formulations for Training Two-Layer ReLU Neural Networks

Karthik Prakhya, Tolga Birdal, Alp Yurtsever

Solving non-convex, NP-hard optimization problems is crucial for training machine learning models, including neural networks. However, non-convexity often leads to black-box machin…

cs.LG2024

Federated Frank-Wolfe Algorithm

Ali Dadras, Sourasekhar Banerjee, Karthik Prakhya +1

Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine…

cs.LG2024

Personalized Multi-tier Federated Learning

Sourasekhar Banerjee, Ali Dadras, Alp Yurtsever +1

The key challenge of personalized federated learning (PerFL) is to capture the statistical heterogeneity properties of data with inexpensive communications and gain customized perf…