Eshaan Nichani
12 papers · 2022–2026 · 5 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (20) ποΈ Keyword Collector (56)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Conference Pioneer
Venues
Top co-authors
Research topics
Machine Learning
(12)
Optimization & Theory Β· Machine Learning
(11)
Artificial Intelligence
(6)
Deep Learning
(5)
Core AI
(4)
Core Methods
(4)
Architectures
(3)
Learning Paradigms
(3)
Optimization & Theory Β· Deep Learning
(2)
Computer Science
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Foundations
(1)
Learning Types
(1)
Mathematics
(1)
Keywords
gradient descent
(6)
sample complexity
(6)
transformer
(2)
feature learning
(2)
layer-wise gradient descent
(2)
representation learning
(2)
neural network
(2)
curriculum learning
(1)
causal discovery
(1)
neural tangent kernel
(1)
neural network optimization
(1)
computational complexity
(1)
neural network theory
(1)
random walk
(1)
sequential learning
(1)
fourier analysis
(1)
hierarchical feature learning
(1)
causal structure
(1)
mutual information
(1)
in-context learning
(1)
Papers
On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach
COLT 2026
Learning Compositional Functions with Transformers from Easy-to-Hard Data
COLT 2025
Learning Hierarchical Polynomials of Multiple Nonlinear Features
ICLR 2025
Understanding Factual Recall in Transformers via Associative Memories
ICLR 2025
How Transformers Learn Causal Structure with Gradient Descent
ICML 2024
Learning Hierarchical Polynomials with Three-Layer Neural Networks
ICLR 2024
Fine-Tuning Language Models with Just Forward Passes
NeurIPS 2023
Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
NeurIPS 2023
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
ICLR 2023
Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models
NeurIPS 2023
Causal Structure Discovery between Clusters of Nodes Induced by Latent Factors
CLeaR 2022
Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials
NeurIPS 2022