Amit Daniely

36 papers · 2011–2025 · 7 conferences · across top CS/AI conferences

Achievements

+12 more ↓

🐣 Hot Topic Early Bird 🏃 Academic Marathon (14) 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (11)

🏃 Academic Marathon (14) 🌉 Interdisciplinary Bridge 🐺 Lone Wolf (5) 🔬 Deep Specialist (25) 🏆 Keyword Champion (2) 🗃️ Keyword Collector (118) ⚡ Prolific Year (7) 🚀 Conference Pioneer 📈 Trend Setter 💎 Century Club (36) 🔥 Unstoppable (7) ❓ The Questioner

Conferences

NIPS (14) COLT (12) ALT (4) AISTATS (2) ICLR (2) ICML (1) JMLR (1)

Top co-authors

Shai Shalev-shwartz (9) Gal Vardi (4) Sivan Sabato (3) Yishay Mansour (3) Elad Granot (3) Mariano Schain (3) Nati Srebro (2) Shai Ben-David (2) Alon Cohen (2) Gilad Yehudai (2)

Keywords

sample complexity (9) neural network (9) learning theory (8) multiclass classification (6) pac learning (6) online learning (3) computational complexity (3) kernel methods (3) empirical risk minimization (3) hypothesis class (3) agnostic learning (3) hardness result (3) gradient descent (3) distributed learning (2) generalization bound (2) representation learning (2) approximation algorithm (2) stochastic gradient descent (2) convex optimization (2) halfspace learning (2)

Papers

Locally Optimal Descent for Dynamic Stepsize Scheduling AISTATS 2025 Existence of Adversarial Examples for Random Convolutional Networks via Isoperimetric Inequalities on $\mathbb{SO}(d)$ COLT 2025 RedEx: Beyond Fixed Representation Methods via Convex Optimization ALT 2024 On the Sample Complexity of Two-Layer Networks: Lipschitz Vs. Element-Wise Lipschitz Activation ALT 2024 Multiclass Boosting: Simple and Intuitive Weak Learning Criteria NIPS 2023 Most Neural Networks Are Almost Learnable NIPS 2023 Computational Complexity of Learning Neural Networks: Smoothness and Degeneracy NIPS 2023 An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network ICLR 2023 Monotone Learning COLT 2022 Asynchronous Stochastic Optimization Robust to Arbitrary Delays NIPS 2021 From Local Pseudorandom Generators to Hardness of Learning COLT 2021 Distribution Free Learning with Local Queries ALT 2020 The Implicit Bias of Depth: How Incremental Learning Drives Generalization ICLR 2020 Hardness of Learning Neural Networks with Natural Weights NIPS 2020 Most ReLU Networks Suffer from $\ell^2$ Adversarial Perturbations NIPS 2020 Neural Networks Learning and Memorization with (almost) no Over-Parameterization NIPS 2020 Learning Parities with Neural Networks NIPS 2020 ID3 Learns Juntas for Smoothed Product Distributions COLT 2020 Open Problem: Is Margin Sufficient for Non-Interactive Private Distributed Learning? COLT 2019 Generalization Bounds for Neural Networks via Approximate Description Length NIPS 2019 Locally Private Learning without Interaction Requires Separation NIPS 2019 Learning Rules-First Classifiers AISTATS 2019 Competitive ratio vs regret minimization: achieving the best of both worlds ALT 2019 SGD Learns the Conjugate Kernel Class of the Network NIPS 2017 Depth Separation for Neural Networks COLT 2017 Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity NIPS 2016 Complexity Theoretic Limitations on Learning DNF’s COLT 2016 Multiclass Learnability and the ERM Principle JMLR 2015 A PTAS for Agnostically Learning Halfspaces COLT 2015 Strongly Adaptive Online Learning ICML 2015 The Complexity of Learning Halfspaces using Generalized Linear Methods COLT 2014 Optimal learners for multiclass problems COLT 2014 The price of bandit information in multiclass online classification COLT 2013 More data speeds up training time in learning halfspaces over sparse vectors NIPS 2013 Multiclass Learning Approaches: A Theoretical Comparison with Implications NIPS 2012 Multiclass Learnability and the ERM principle COLT 2011