Publications

On the effect of clients-server communication on the generalization error of federated learning

Generalization analysis of next-token prediction learning algorithms

Impact of data heterogeneity on the generalization error of distributed learning algorithms

Tighter CMI-based generalization bounds via projection and quantization

Generalization guarantees for representation learning via data-dependent Gaussian mixture priors

Multi-view representation learning regularizer with Gaussian-product mixture prior

Lessons from generalization error analysis of federated learning: you may communicate less often!

Data-dependent generalization bounds via variable-size compressibility

Minimal communication-cost statistical learning

Minimum description length and generalization guarantees for representation learning

More communication does not result in smaller generalization error in federated learning

Rate-distortion theoretic bounds on generalization error for distributed learning

Rate-distortion theoretic generalization bounds for stochastic learning algorithms

Heavy tails in SGD and compressibility of overparametrized neural networks

Lower bound on the capacity of the continuous-space SSFM model of optical fiber

Zero-error sum modulo two with a common observation

On the capacity of the continuous-space SSFM model of optical fiber

Distributed function computation over a rooted directed tree

On Körner-Marton’s sum modulo two problem

On cooperation in multi-terminal computation and rate distortion

Computing a function of correlated sources

Distributed function computation over a tree network

On function computation over a cascade network

On cooperation in multi-terminal computation and rate distortion

Computing a function of correlated sources: a rate region

Reliable source transmission over relay networks with side information