Skip to content

Yatin Dandi

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

11

Venues

5

Active years

2020–2026

Best venue rank

A*

Where they publish

Papers

11 indexed papers, newest first.

YearVenueTitleAuthors
2026COLTRigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method.Yatin Dandi, David Gamarnik, Francisco Pernice, Lenka Zdeborov
2026COLTProvable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining.Yunwei Ren, Yatin Dandi, Florent Krzakala, Jason D. Lee
2025AISTATSA Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities.Yatin Dandi, Luca Pesce, Hugo Cui, Florent Krzakala, Yue M. Lu, Bruno Loureiro
2025AISTATSFundamental computational limits of weak learnability in high-dimensional multi-index models.Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborov, Bruno Loureiro, Florent Krzakala
2025ICMLFundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds.Emanuele Troiani, Hugo Cui, Yatin Dandi, Florent Krzakala, Lenka Zdeborov
2024ICMLOnline Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs.Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan
2024ICMLAsymptotics of feature learning in two-layer networks after one gradient-step.Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue M. Lu, Lenka Zdeborov, Bruno Loureiro
2024ICMLThe Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents.Yatin Dandi, Emanuele Troiani, Luca Arnaboldi, Luca Pesce, Lenka Zdeborov, Florent Krzakala
2022AAAIImplicit Gradient Alignment in Distributed and Federated Learning.Yatin Dandi, Luis Barba, Martin Jaggi
2021AAAIGeneralized Adversarially Learned Inference.Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai
2020WACVJointly Trained Image and Video Generation using Residual Vectors.Yatin Dandi, Aniket Das, Soumye Singhal, Vinay P. Namboodiri, Piyush Rai