← Authors

Surbhi Goel

35 papers · 2017–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (5) πŸƒ Academic Marathon (8) 🐝 Cross-Pollinator (9) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (49) πŸ”¬ Deep Specialist (14) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown ⚑ Prolific Year (6) πŸ—ƒοΈ Keyword Collector (133) πŸ”₯ Unstoppable (9) πŸ’Ž Century Club (35)

Conferences

NIPS (12) ICML (10) COLT (6) ICLR (5) AISTATS (2)

Top co-authors

Cyril Zhang (9) Adam Klivans (8) Akshay Krishnamurthy (6) Sham Kakade (6) Jordan Ash (4) Sushrut Karmalkar (3) Eran Malach (3) Adam R. Klivans (3) Bingbin Liu (3) Raghu Meka (2)

Keywords

neural network (7) learning theory (4) ising model (3) inductive bia (3) graphical model (3) relu activation (3) gradient descent (3) lower bound (2) representation learning (2) relu network (2) square loss (2) convolutional neural network (2) stochastic gradient descent (2) feature learning (2) surrogate loss (2) structure learning (2) isotonic regression (2) sample complexity (2) neural network optimization (2) approximation algorithm (2)

Papers

Conformal Language Model Reasoning with Coherent Factuality ICLR 2025
Progressive distillation induces an implicit curriculum ICLR 2025
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference ICLR 2025
A Theory of Learning with Autoregressive Chain of Thought COLT 2025
Tolerant Algorithms for Learning with Arbitrary Covariate Shift NIPS 2024
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains NIPS 2024
Stochastic Bandits with ReLU Neural Networks ICML 2024
Complexity Matters: Feature Learning in the Presence of Spurious Correlations ICML 2024
Exposing Attention Glitches with Flip-Flop Language Modeling NIPS 2023
Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck NIPS 2023
Transformers Learn Shortcuts to Automata ICLR 2023
Learning Narrow One-Hidden-Layer ReLU Networks COLT 2023
Adversarial Resilience in Sequential Prediction via Abstention NIPS 2023
Investigating the Role of Negatives in Contrastive Representation Learning AISTATS 2022
Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms NIPS 2022
Understanding Contrastive Learning Requires Incorporating Inductive Biases ICML 2022
Inductive Biases and Variable Creation in Self-Attention Mechanisms ICML 2022
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NIPS 2022
Anti-Concentrated Confidence Bonuses For Scalable Exploration ICLR 2022
Acceleration via Fractal Learning Rate Schedules ICML 2021
Statistical Estimation from Dependent Data ICML 2021
Gone Fishing: Neural Active Learning with Fisher Embeddings NIPS 2021
Approximation Schemes for ReLU Regression COLT 2020
Statistical-Query Lower Bounds via Functional Gradients NIPS 2020
From Boltzmann Machines to Neural Networks and Back Again NIPS 2020
Learning Ising and Potts Models with Latent Variables AISTATS 2020
Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent ICML 2020
Learning Mixtures of Graphs from Epidemic Cascades ICML 2020
Efficiently Learning Adversarially Robust Halfspaces with Noise ICML 2020
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time COLT 2019
Learning Ising Models with Independent Failures COLT 2019
Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals NIPS 2019
Learning One Convolutional Layer with Overlapping Patches ICML 2018
Eigenvalue Decay Implies Polynomial-Time Learnability for Neural Networks NIPS 2017
Reliably Learning the ReLU in Polynomial Time COLT 2017