Behnam Neyshabur

34 papers · 2013–2023 · 4 conferences · across top CS/AI conferences

Achievements

+14 more ↓

🌍 Conference Polyglot (4) 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🏃 Academic Marathon (10)

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🏃 Academic Marathon (10) 🌟 Keyword Trendsetter Combo (4) 🏆 Keyword Champion 🧬 Topic Evolution 👑 Triple Crown ⚡ Prolific Year (9) 📈 Trend Setter 🗃️ Keyword Collector (90) 💎 Century Club (34) ❓ The Questioner (3) 🔥 Unstoppable (9) 🚀 Conference Pioneer

Conferences

ICLR (16) NIPS (13) ICML (3) COLT (2)

Top co-authors

Hanie Sedghi (7) Nati Srebro (6) Srinadh Bhojanapalli (5) Ethan Dyer (4) Yuhuai Wu (4) Nathan Srebro (4) Anders Andreassen (3) Ruslan Salakhutdinov (3) Guy Gur-Ari (3) Vinay Ramasesh (2)

Keywords

language modeling (2) generalization bound (2) deep neural network (2) gradient descent (2) stochastic gradient descent (2) image classification (2) recurrent neural network (2) matrix factorization (2) metric learning (1) mathematical reasoning (1) neural network compression (1) in-context learning (1) neural machine translation (1) out-of-distribution generalization (1) similarity search (1) loss landscape (1) neural network optimization (1) transfer learning (1) deep learning (1) neural architecture search (1)

Papers

Long Range Language Modeling via Gated State Spaces ICLR 2023 REPAIR: REnormalizing Permuted Activations for Interpolation Repair ICLR 2023 Solving Quantitative Reasoning Problems with Language Models NIPS 2022 A Loss Curvature Perspective on Training Instabilities of Deep Learning Models ICLR 2022 Data Scaling Laws in NMT: The Effect of Noise and Architecture ICML 2022 Revisiting Neural Scaling Laws in Language and Vision NIPS 2022 Block-Recurrent Transformers NIPS 2022 Exploring Length Generalization in Large Language Models NIPS 2022 The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks ICLR 2022 Leveraging unlabeled data to predict out-of-distribution performance ICLR 2022 Exploring the Limits of Large Scale Pre-training ICLR 2022 Understanding the failure modes of out-of-distribution generalization ICLR 2021 When Do Curricula Work? ICLR 2021 The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers ICLR 2021 Sharpness-aware Minimization for Efficiently Improving Generalization ICLR 2021 Are wider nets better given the same number of parameters? ICLR 2021 Deep Learning Through the Lens of Example Difficulty NIPS 2021 Extreme Memorization via Scale of Initialization ICLR 2021 The intriguing role of module criticality in the generalization of deep networks ICLR 2020 What is being transferred in transfer learning? NIPS 2020 Towards Learning Convolutions from Scratch NIPS 2020 Observational Overfitting in Reinforcement Learning ICLR 2020 The role of over-parametrization in generalization of neural networks ICLR 2019 A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks ICLR 2018 Stronger Generalization Bounds for Deep Nets via a Compression Approach ICML 2018 Exploring Generalization in Deep Learning NIPS 2017 Corralling a Band of Bandit Algorithms COLT 2017 Implicit Regularization in Matrix Factorization NIPS 2017 Global Optimality of Local Search for Low Rank Matrix Recovery NIPS 2016 Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations NIPS 2016 Path-SGD: Path-Normalized Optimization in Deep Neural Networks NIPS 2015 Norm-Based Capacity Control in Neural Networks COLT 2015 On Symmetric and Asymmetric LSHs for Inner Product Search ICML 2015 The Power of Asymmetry in Binary Hashing NIPS 2013