Cikkek nyilvánosan hozzáférhető megbízással - Mikhail KhodakTovábbi információ
Valahol hozzáférhető: 17
Adaptive gradient-based meta-learning methods
M Khodak, MF Balcan, A Talwalkar
NeurIPS, 2019
Megbízások: US National Science Foundation, US Department of Defense
Federated hyperparameter tuning: Challenges, baselines, and connections to weight-sharing
M Khodak, R Tu, T Li, L Li, MFF Balcan, V Smith, A Talwalkar
Advances in Neural Information Processing Systems 34, 19184-19197, 2021
Megbízások: US National Science Foundation, US Department of Defense
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks
R Tu, N Roberts, M Khodak, J Shen, F Sala, A Talwalkar
Megbízások: US National Science Foundation, US Department of Defense
Cross-modal fine-tuning: Align then refine
J Shen, L Li, LM Dery, C Staten, M Khodak, G Neubig, A Talwalkar
International Conference on Machine Learning, 31030-31056, 2023
Megbízások: US National Science Foundation
A compressed sensing view of unsupervised text embeddings, bag-of-n-grams, and LSTMs
S Arora, M Khodak, N Saunshi, K Vodrahalli
ICLR, 2018
Megbízások: US National Science Foundation, US Department of Defense
Automated wordnet construction using word embeddings
M Khodak, A Risteski, C Fellbaum, S Arora
SENSE, 12-23, 2017
Megbízások: US National Science Foundation, US Department of Defense
Efficient architecture search for diverse tasks
J Shen, M Khodak, A Talwalkar
Advances in Neural Information Processing Systems 35, 16151-16164, 2022
Megbízások: US National Science Foundation, US Department of Defense
Rethinking neural operations for diverse tasks
N Roberts, M Khodak, T Dao, L Li, C Ré, A Talwalkar
Advances in Neural Information Processing Systems 34, 15855-15869, 2021
Megbízások: US National Science Foundation, US Department of Defense, US National …
Learning cloud dynamics to optimize spot instance bidding strategies
M Khodak, L Zheng, AS Lan, C Joe-Wong, M Chiang
INFOCOM, 2762-2770, 2018
Megbízások: US National Science Foundation, US Department of Defense
Learning predictions for algorithms with predictions
M Khodak, MFF Balcan, A Talwalkar, S Vassilvitskii
Advances in Neural Information Processing Systems 35, 3542-3555, 2022
Megbízások: US National Science Foundation, US Department of Defense
A sample complexity separation between non-convex and convex meta-learning
N Saunshi, Y Zhang, M Khodak, S Arora
ICML, 2020
Megbízások: US National Science Foundation, US Department of Defense
Provably tuning the ElasticNet across instances
MFF Balcan, M Khodak, D Sharma, A Talwalkar
Advances in Neural Information Processing Systems 35, 27769-27782, 2022
Megbízások: US National Science Foundation, US Department of Defense
Learning-to-learn non-convex piecewise-Lipschitz functions
MFF Balcan, M Khodak, D Sharma, A Talwalkar
Advances in Neural Information Processing Systems 34, 15056-15069, 2021
Megbízások: US National Science Foundation, US Department of Defense
Automl decathlon: Diverse tasks, modern methods, and efficiency at scale
N Roberts, S Guo, C Xu, A Talwalkar, D Lander, L Tao, L Cai, S Niu, ...
NeurIPS 2022 Competition Track, 151-170, 2023
Megbízások: US National Science Foundation
Meta-learning adversarial bandit algorithms
M Khodak, I Osadchiy, K Harris, MFF Balcan, KY Levy, R Meir, SZ Wu
Advances in Neural Information Processing Systems 36, 35441-35471, 2023
Megbízások: US National Science Foundation, US Department of Defense
On noisy evaluation in federated hyperparameter tuning
K Kuo, P Thaker, M Khodak, J Nguyen, D Jiang, A Talwalkar, V Smith
Proceedings of Machine Learning and Systems 5, 127-144, 2023
Megbízások: US National Science Foundation
L2G: Repurposing Language Models for Genomics Tasks
W Cheng, J Shen, M Khodak, J Ma, A Talwalkar
bioRxiv, 2024.12. 09.627422, 2024
Megbízások: Chan Zuckerberg Initiative
A publikációs és a finanszírozási adatokat számítógépes program határozza meg, automatikusan.