Yatin Dandi
13 papers · 2020–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🌍 Conference Polyglot · Silver 🗺️ Taxonomy Completionist (29) 🏃 Academic Marathon · Sprint 🧬 Topic Evolution
🗃️
Keyword Collector
(61)
🔥
Unstoppable · Bronze
🚀
Conference Pioneer
📈
Trend Setter
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(12)
Deep Learning
(10)
Optimization & Theory · Machine Learning
(10)
Mathematics & Optimization
(4)
Architectures
(4)
Optimization & Theory · Deep Learning
(4)
Core Methods
(3)
Learning Types
(3)
Mathematics
(3)
Models
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Application Areas
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
gradient descent
(4)
feature learning
(3)
generalization error
(2)
batch size
(2)
dynamical mean field theory
(2)
approximate message passing
(2)
information exponent
(2)
latent variable
(2)
self-supervised learning
(1)
neural network optimization
(1)
video generation
(1)
empirical risk minimization
(1)
stochastic gradient descent
(1)
adversarial training
(1)
distributed learning
(1)
image generation
(1)
random matrix theory
(1)
nonlinear function
(1)
deep learning theory
(1)
hierarchical feature learning
(1)
Papers
Provable Learning of Random Hierarchy Models and Hierarchical Shallow-to-Deep Chaining
COLT 2026
Rigorous Asymptotics for First-Order Algorithms Through the Dynamical Cavity Method
COLT 2026
A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities
AISTATS 2025
Fundamental computational limits of weak learnability in high-dimensional multi-index models
AISTATS 2025
Fundamental limits of learning in sequence multi-index models and deep attention networks: high-dimensional asymptotics and sharp thresholds
ICML 2025
Asymptotics of feature learning in two-layer networks after one gradient-step
ICML 2024
How Two-Layer Neural Networks Learn, One (Giant) Step at a Time
JMLR 2024
Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
ICML 2024
The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents
ICML 2024
Universality laws for Gaussian mixtures in generalized linear models
NeurIPS 2023
Implicit Gradient Alignment in Distributed and Federated Learning
AAAI 2022
Generalized Adversarially Learned Inference
AAAI 2021
Jointly Trained Image and Video Generation using Residual Vectors
WACV 2020