Mikhail Khodak

19 papers · 2018–2025 · 4 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🌍 Conference Polyglot (4) 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (7)

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge 🤝 Dynamic Duo (10) 🗃️ Keyword Collector (55) ⚡ Prolific Year (5) 🚀 Conference Pioneer 📈 Trend Setter 💎 Century Club (19)

Conferences

ICLR (8) ICML (5) NIPS (5) ACL (1)

Top co-authors

Ameet Talwalkar (10) Sanjeev Arora (4) Nikunj Saunshi (4) Liam Li (4) Maria-Florina F Balcan (3) Junhong Shen (2) Lester Mackey (2) Lucio M. Dery (2) Graham Neubig (2) Jeffrey Li (1)

Research topics

Differential Privacy (1)

Keywords

transfer learning (4) sample complexity (2) online convex optimization (2) neural architecture search (2) non-convex optimization (2) representation learning (2) regret bound (2) domain adaptation (2) federated learning (2) cross-modal learning (1) multimodal learning (1) online learning (1) gradient-based optimization (1) hyperparameter optimization (1) few-shot learning (1) algorithm design (1) gradient descent (1) neural network optimization (1) weight sharing (1) contrastive learning (1)

Papers

Specialized Foundation Models Struggle to Beat Supervised Baselines ICLR 2025 SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation NIPS 2024 Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances ICLR 2024 Meta-Learning in Games ICLR 2023 AANG : Automating Auxiliary Learning ICLR 2023 Cross-Modal Fine-Tuning: Align then Refine ICML 2023 Learning-augmented private algorithms for multiple quantile release ICML 2023 Geometry-Aware Gradient Algorithms for Neural Architecture Search ICLR 2021 Learning-to-learn non-convex piecewise-Lipschitz functions NIPS 2021 Rethinking Neural Operations for Diverse Tasks NIPS 2021 Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing NIPS 2021 Initialization and Regularization of Factorized Neural Layers ICLR 2021 Differentially Private Meta-Learning ICLR 2020 A Sample Complexity Separation between Non-Convex and Convex Meta-Learning ICML 2020 Adaptive Gradient-Based Meta-Learning Methods NIPS 2019 A Theoretical Analysis of Contrastive Unsupervised Representation Learning ICML 2019 Provable Guarantees for Gradient-Based Meta-Learning ICML 2019 A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs ICLR 2018 A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors ACL 2018