1 citations · 1 across the 4 of their papers we have counts for
6 papers
Generalization Bounds for Flow-matching Generative Models for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped. Existing analyses often impose restrictive assu…
Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
Despite the remarkable empirical success of score-based diffusion models, their statistical guarantees remain underdeveloped. Existing analyses often provide pessimistic convergenc…
A Statistical Analysis for Supervised Deep Learning with Exponential Families for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Peter L. Bartlett
Recent advances have revealed that the rate of convergence of the expected test error in deep supervised learning decays as a function of the intrinsic dimension and not the dimens…
A Statistical Analysis of Deep Federated Learning for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Peter L. Bartlett
Despite significant research on the optimization aspects of federated learning, the exploration of generalization error, especially in the realm of heterogeneous federated learning…
A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
Saptarshi Chakraborty, Peter L. Bartlett
Variational Autoencoders (VAEs) have gained significant popularity among researchers as a powerful tool for understanding unknown distributions based on limited samples. This popul…
On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension
Saptarshi Chakraborty, Peter L. Bartlett
Despite the remarkable empirical successes of Generative Adversarial Networks (GANs), the theoretical guarantees for their statistical accuracy remain rather pessimistic. In partic…