6 papers · 1 filter
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…
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…
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…
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…
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…
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…