← Authors

Suriya Gunasekar

24 papers · 2014–2024 · 8 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (7) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (37) 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (10) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ—ƒοΈ Keyword Collector (89) πŸ’Ž Century Club (24) πŸ”₯ Unstoppable (11) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer

Conferences

NIPS (8) ICML (4) AISTATS (3) COLT (3) ICLR (3) ECCV (1) JMLR (1) MLHC (1)

Top co-authors

Nathan Srebro (7) Daniel Soudry (7) Jason Lee (5) Nati Srebro (4) Joydeep Ghosh (3) Mor Shpigel Nacson (3) Blake Woodworth (3) Blake E Woodworth (2) Besmira Nushi (2) Mert Yuksekgonul (2)

Keywords

gradient descent (9) implicit bia (5) matrix completion (4) implicit regularization (4) representation learning (2) learning theory (2) equalized odd (2) algorithmic fairness (2) convergence rate (2) gradient flow (2) low-rank matrix (2) separable datum (2) kernel regime (2) convex optimization (2) natural gradient (2) mirror descent (2) deep learning (1) sample complexity (1) online learning (1) data augmentation (1)

Papers

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models ICLR 2024
KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval ICLR 2024
How to Fine-Tune Vision Models with SGD ICLR 2024
(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability NIPS 2023
Neural-Sim: Learning to Generate Training Data with NeRF ECCV 2022
Inductive Bias of Multi-Channel Linear Convolutional Networks with Bounded Weight Norm COLT 2022
Data Augmentation as Feature Manipulation ICML 2022
Mirrorless Mirror Descent: A Natural Derivation of Mirror Descent AISTATS 2021
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NIPS 2020
Implicit Regularization and Convergence for Weight Normalization NIPS 2020
Kernel and Rich Regimes in Overparametrized Models COLT 2020
Convergence of Gradient Descent on Separable Data AISTATS 2019
Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Models ICML 2019
Characterizing Implicit Bias in Terms of Optimization Geometry ICML 2018
The Implicit Bias of Gradient Descent on Separable Data JMLR 2018
On preserving non-discrimination when combining expert advice NIPS 2018
Implicit Bias of Gradient Descent on Linear Convolutional Networks NIPS 2018
Learning Non-Discriminatory Predictors COLT 2017
Implicit Regularization in Matrix Factorization NIPS 2017
Identifiable Phenotyping using Constrained Non-Negative Matrix Factorization MLHC 2016
Preference Completion from Partial Rankings NIPS 2016
Consistent Collective Matrix Completion under Joint Low Rank Structure AISTATS 2015
Unified View of Matrix Completion under General Structural Constraints NIPS 2015
Exponential Family Matrix Completion under Structural Constraints ICML 2014