Yatin Dandi

According to our database, Yatin Dandi authored at least 23 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula.

Matteo Vilucchio, Yatin Dandi, Cédric Gerbelot, Florent Krzakala

CoRR, February, 2025

The Computational Advantage of Depth: Learning High-Dimensional Hierarchical Functions with Gradient Descent.

Yatin Dandi, Luca Pesce, Lenka Zdeborová, Florent Krzakala

CoRR, February, 2025

Optimal Spectral Transitions in High-Dimensional Multi-Index Models.

Leonardo Defilippis, Yatin Dandi, Pierre Mergny, Florent Krzakala, Bruno Loureiro

CoRR, February, 2025

Fundamental 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 Zdeborová

CoRR, February, 2025

Fundamental computational limits of weak learnability in high-dimensional multi-index models.

Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

A 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

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Online Learning and Information Exponents: On The Importance of Batch size, and Time/Complexity Tradeoffs.

Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan

CoRR, 2024

Fundamental limits of weak learnability in high-dimensional multi-index models.

Emanuele Troiani, Yatin Dandi, Leonardo Defilippis, Lenka Zdeborová, Bruno Loureiro, Florent Krzakala

CoRR, 2024

Repetita Iuvant: Data Repetition Allows SGD to Learn High-Dimensional Multi-Index Functions.

Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Luca Pesce, Ludovic Stephan

CoRR, 2024

The 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 Zdeborová, Florent Krzakala

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Asymptotics of feature learning in two-layer networks after one gradient-step.

Hugo Cui, Luca Pesce, Yatin Dandi, Florent Krzakala, Yue M. Lu, Lenka Zdeborová, Bruno Loureiro

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs.

Luca Arnaboldi, Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

A Gentle Introduction to Gradient-Based Optimization and Variational Inequalities for Machine Learning.

Neha S. Wadia, Yatin Dandi, Michael I. Jordan

CoRR, 2023

Sampling with flows, diffusion and autoregressive neural networks: A spin-glass perspective.

Davide Ghio, Yatin Dandi, Florent Krzakala, Lenka Zdeborová

CoRR, 2023

Learning Two-Layer Neural Networks, One (Giant) Step at a Time.

Yatin Dandi, Florent Krzakala, Bruno Loureiro, Luca Pesce, Ludovic Stephan

CoRR, 2023

Universality laws for Gaussian mixtures in generalized linear models.

Yatin Dandi, Ludovic Stephan, Florent Krzakala, Bruno Loureiro, Lenka Zdeborová

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Data-heterogeneity-aware Mixing for Decentralized Learning.

Yatin Dandi, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich

CoRR, 2022

Implicit Gradient Alignment in Distributed and Federated Learning.

Yatin Dandi, Luis Barba, Martin Jaggi

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

NeurInt : Learning to Interpolate through Neural ODEs.

Avinandan Bose, Aniket Das, Yatin Dandi, Piyush Rai

CoRR, 2021

Understanding Layer-wise Contributions in Deep Neural Networks through Spectral Analysis.

Yatin Dandi, Arthur Jacot

CoRR, 2021

Generalized Adversarially Learned Inference.

Yatin Dandi, Homanga Bharadhwaj, Abhishek Kumar, Piyush Rai

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Jointly Trained Image and Video Generation using Residual Vectors.

Yatin Dandi, Aniket Das, Soumye Singhal, Vinay P. Namboodiri, Piyush Rai

Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020

Model-Agnostic Learning to Meta-Learn.

Arnout Devos, Yatin Dandi

Proceedings of the NeurIPS 2020 Workshop on Pre-registration in Machine Learning, 2020