Scholar

Yatin Dandi

Google Scholar ID: UiEzYkMAAAAJ

EPFL, IIT Kanpur

Deep Learning TheoryStatistical PhysicsOptimization

Google Scholar↗

Citations & Impact

All-time

Citations

445

H-index

10

i10-index

11

Publications

20

Co-authors

19

list available

Contact

No contact links provided.

Publications

10 items

Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method

2026

Cited

0

Deep Learning of Compositional Targets with Hierarchical Spectral Methods

2026

Cited

0

Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining

2026

Cited

0

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

2025

Cited

0

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

2025

Cited

0

Optimal Spectral Transitions in High-Dimensional Multi-Index Models

2025

Cited

0

Fundamental limits of learning in sequence multi-index models and deep attention networks: High-dimensional asymptotics and sharp thresholds

2025

Cited

0

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

arXiv.org · 2024

Cited

8

Resume (English only)

Co-authors

19 total

Florent Krzakala

École polytechnique fédérale de Lausanne

Lenka Zdeborová

EPFL, Switzerland

École Normale Supérieure & CNRS

PhD student, EPFL

Ludovic Stephan

Assistant Professor, ENSAI

Gordon McKay Professor of Electrical Engineering and of Applied Mathematics, Harvard University