← Authors

Sanjeev Arora

64 papers · 2012–2025 · 6 conferences · across top CS/AI conferences

Achievements

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (13) πŸƒ Academic Marathon (13) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (6) πŸ—ΊοΈ Taxonomy Completionist (21) 🏠 Conference Loyalist (21) πŸ† Keyword Champion πŸ‘‘ Triple Crown πŸ‘₯ Mega-Team (22) πŸ”¬ Deep Specialist (12) 🀝 Dynamic Duo (15) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (14) ❓ The Questioner (7) ⚑ Prolific Year (10) πŸ’Ž Century Club (64) πŸ—ƒοΈ Keyword Collector (57) πŸ“ˆ Trend Setter

Conferences

ICML (21) NIPS (19) ICLR (17) COLT (4) EMNLP (2) ACL (1)

Top co-authors

Zhiyuan Li (15) Nikunj Saunshi (11) Rong Ge (11) Sadhika Malladi (10) Kaifeng Lyu (10) Dingli Yu (9) Yi Zhang (8) Danqi Chen (7) Abhishek Panigrahi (7) Wei Hu (6)

Keywords

gradient descent (9) neural network optimization (6) representation learning (5) sample complexity (4) non-convex optimization (4) generalization bound (3) federated learning (3) neural network (3) stochastic differential equation (3) language model fine-tuning (3) learning rate (2) contrastive learning (2) data privacy (2) generative model (2) neural tangent kernel (2) sparse recovery (2) batch normalization (2) sparse coding (2) dictionary learning (2) benchmark evaluation (2)

Papers

On the Power of Context-Enhanced Learning in LLMs ICML 2025
Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs? ICML 2025
Weak-to-Strong Generalization Even in Random Feature Networks, Provably ICML 2025
Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning ICLR 2025
Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization ICLR 2025
Provable unlearning in topic modeling and downstream tasks ICLR 2025
SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models ICLR 2024
LESS: Selecting Influential Data for Targeted Instruction Tuning ICML 2024
Trainable Transformer in Transformer ICML 2024
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving NIPS 2024
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty NIPS 2024
Can Models Learn Skill Composition from Examples? NIPS 2024
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs NIPS 2024
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates NIPS 2024
Language Models as Science Tutors ICML 2024
A Quadratic Synchronization Rule for Distributed Deep Learning ICLR 2024
Task-Specific Skill Localization in Fine-tuned Language Models ICML 2023
A Kernel-Based View of Language Model Fine-Tuning ICML 2023
Understanding Influence Functions and Datamodels via Harmonic Analysis ICLR 2023
Fine-Tuning Language Models with Just Forward Passes NIPS 2023
Why (and When) does Local SGD Generalize Better than SGD? ICLR 2023
Do Transformers Parse while Predicting the Masked Word? EMNLP 2023
Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction NIPS 2022
Understanding Gradient Descent on the Edge of Stability in Deep Learning ICML 2022
On Predicting Generalization using GANs ICLR 2022
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework ICLR 2022
Understanding Contrastive Learning Requires Incorporating Inductive Biases ICML 2022
On the SDEs and Scaling Rules for Adaptive Gradient Algorithms NIPS 2022
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound NIPS 2022
Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent NIPS 2022
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks ICLR 2021
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning NIPS 2021
On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs) NIPS 2021
Gradient Descent on Two-layer Nets: Margin Maximization and Simplicity Bias NIPS 2021
Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets? ICLR 2021
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning ICML 2020
InstaHide: Instance-hiding Schemes for Private Distributed Learning ICML 2020
Provable Representation Learning for Imitation Learning via Bi-level Optimization ICML 2020
Harnessing the Power of Infinitely Wide Deep Nets on Small-data Tasks ICLR 2020
An Exponential Learning Rate Schedule for Deep Learning ICLR 2020
Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality NIPS 2020
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate NIPS 2020
TextHide: Tackling Data Privacy in Language Understanding Tasks EMNLP 2020
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets NIPS 2019
A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks ICLR 2019
Theoretical Analysis of Auto Rate-Tuning by Batch Normalization ICLR 2019
Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks ICML 2019
A Theoretical Analysis of Contrastive Unsupervised Representation Learning ICML 2019
On Exact Computation with an Infinitely Wide Neural Net NIPS 2019
Implicit Regularization in Deep Matrix Factorization NIPS 2019
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors ACL 2018
Stronger Generalization Bounds for Deep Nets via a Compression Approach ICML 2018
A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs ICLR 2018
Do GANs learn the distribution? Some Theory and Empirics ICLR 2018
An Analysis of the t-SNE Algorithm for Data Visualization COLT 2018
On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization ICML 2018
On the Ability of Neural Nets to Express Distributions COLT 2017
Generalization and Equilibrium in Generative Adversarial Nets (GANs) ICML 2017
Provable Algorithms for Inference in Topic Models ICML 2016
Simple, Efficient, and Neural Algorithms for Sparse Coding COLT 2015
New Algorithms for Learning Incoherent and Overcomplete Dictionaries COLT 2014
Provable Bounds for Learning Some Deep Representations ICML 2014
A Practical Algorithm for Topic Modeling with Provable Guarantees ICML 2013
Provable ICA with Unknown Gaussian Noise, with Implications for Gaussian Mixtures and Autoencoders NIPS 2012