← Authors

Michael Carbin

15 papers · 2019–2025 · 6 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (28) 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (6) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (12) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”₯ Unstoppable (7) ❓ The Questioner πŸ’Ž Century Club (15)

Conferences

ICML (5) ICLR (4) NIPS (3) AAAI (1) CVPR (1) IJCAI (1)

Top co-authors

Jonathan Frankle (8) Gintare Karolina Dziugaite (4) Cambridge Yang (3) Tian Jin (3) Alex Renda (3) Daniel Roy (2) Dr.Saman Amarasinghe (2) Yang Zhang (2) Jonathan Ragan-Kelley (2) Shiyu Chang (2)

Keywords

neural network pruning (3) lottery ticket hypothesis (3) model compression (3) transfer learning (2) reinforcement learning (2) sparse training (2) network pruning (2) sample complexity (2) model pruning (1) optimal policy (1) deep neural network (1) scaling law (1) model generalization (1) linear mode connectivity (1) self-supervised pre-training (1) compiler optimization (1) linear temporal logic (1) hierarchical lstm (1) unstructured pruning (1) network compression (1)

Papers

Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding ICML 2025
Learning to Compile Programs to Neural Networks ICML 2024
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning ICLR 2024
Computably Continuous Reinforcement-Learning Objectives Are PAC-Learnable AAAI 2023
Pruning’s Effect on Generalization Through the Lens of Training and Regularization NIPS 2022
On the (In)Tractability of Reinforcement Learning for LTL Objectives IJCAI 2022
Pruning Neural Networks at Initialization: Why Are We Missing the Mark? ICLR 2021
The Lottery Tickets Hypothesis for Supervised and Self-Supervised Pre-Training in Computer Vision Models CVPR 2021
On the Predictability of Pruning Across Scales ICML 2021
Linear Mode Connectivity and the Lottery Ticket Hypothesis ICML 2020
The Lottery Ticket Hypothesis for Pre-trained BERT Networks NIPS 2020
Comparing Rewinding and Fine-tuning in Neural Network Pruning ICLR 2020
Ithemal: Accurate, Portable and Fast Basic Block Throughput Estimation using Deep Neural Networks ICML 2019
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks ICLR 2019
Compiler Auto-Vectorization with Imitation Learning NIPS 2019