Kevin Swersky

30 papers · 2010–2026 · 9 conferences · across top CS/AI conferences

Achievements

+13 more ↓

🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (15) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (9)

🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (4) 👑 Triple Crown 🧬 Topic Evolution 💎 Century Club (30) ⚡ Prolific Year (8) 🚀 Conference Pioneer 📈 Trend Setter ❓ The Questioner 🔥 Unstoppable (8) 🗃️ Keyword Collector (127)

Conferences

ICML (10) ICLR (7) NIPS (7) AISTATS (1) CVPR (1) ICCV (1) JMLR (1) UAI (1) WACV (1)

Top co-authors

Milad Hashemi (8) Daniel Tarlow (4) Parthasarathy Ranganathan (4) Jasper Snoek (4) Rich Zemel (4) Richard Zemel (3) David Duvenaud (3) Richard S. Zemel (3) Mohammad Norouzi (3) Ryan P. Adams (3)

Keywords

bayesian optimization (5) representation learning (4) gaussian process (4) generative model (3) neural network (3) hyperparameter optimization (3) multi-task learning (3) metric learning (2) zero-shot learning (2) restricted boltzmann machine (2) probabilistic model (2) distance metric (2) hyperparameter tuning (2) acquisition function (2) transfer learning (1) binary classification (1) black-box optimization (1) imitation learning (1) benchmark evaluation (1) image classification (1)

Papers

Do Generative Video Models Understand Physical Principles? WACV 2026 Pre-trained Gaussian Processes for Bayesian Optimization JMLR 2024 Directly Fine-Tuning Diffusion Models on Differentiable Rewards ICLR 2024 CUF: Continuous Upsampling Filters CVPR 2023 Data-Driven Offline Optimization for Architecting Hardware Accelerators ICLR 2022 Oops I Took A Gradient: Scalable Sampling for Discrete Distributions ICML 2021 No MCMC for me: Amortized sampling for fast and stable training of energy-based models ICLR 2021 Amortized Bayesian Optimization over Discrete Spaces UAI 2020 An Imitation Learning Approach for Cache Replacement ICML 2020 Optimizing Long-term Social Welfare in Recommender Systems: A Constrained Matching Approach ICML 2020 Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples ICLR 2020 Your classifier is secretly an energy based model and you should treat it like one ICLR 2020 LEARNING EXECUTION THROUGH NEURAL CODE FUSION ICLR 2020 Neural Execution Engines: Learning to Execute Subroutines NIPS 2020 Big Self-Supervised Models are Strong Semi-Supervised Learners NIPS 2020 Graph Normalizing Flows NIPS 2019 Flexibly Fair Representation Learning by Disentanglement ICML 2019 Meta-Learning for Semi-Supervised Few-Shot Classification ICLR 2018 Learning Memory Access Patterns ICML 2018 Prototypical Networks for Few-shot Learning NIPS 2017 Generative Moment Matching Networks ICML 2015 Scalable Bayesian Optimization Using Deep Neural Networks ICML 2015 Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions ICCV 2015 Input Warping for Bayesian Optimization of Non-Stationary Functions ICML 2014 Stochastic k-Neighborhood Selection for Supervised and Unsupervised Learning ICML 2013 Learning Fair Representations ICML 2013 Multi-Task Bayesian Optimization NIPS 2013 Cardinality Restricted Boltzmann Machines NIPS 2012 Probabilistic n-Choose-k Models for Classification and Ranking NIPS 2012 Inductive Principles for Restricted Boltzmann Machine Learning AISTATS 2010