Liam Collins

According to our database, Liam Collins authored at least 13 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness.

Liam Collins, Advait Parulekar, Aryan Mokhtari, Sujay Sanghavi, Sanjay Shakkottai

CoRR, 2024

Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks.

Liam Collins, Hamed Hassani, Mahdi Soltanolkotabi, Aryan Mokhtari, Sanjay Shakkottai

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning.

Liam Collins, Shanshan Wu, Sewoong Oh, Khe Chai Sim

CoRR, 2023

Meta-Learning for Image-Guided Millimeter-Wave Beam Selection in Unseen Environments.

Jerry Gu, Liam Collins, Debashri Roy, Aryan Mokhtari, Sanjay Shakkottai, Kaushik R. Chowdhury

Proceedings of the IEEE International Conference on Acoustics, 2023

InfoNCE Loss Provably Learns Cluster-Preserving Representations.

Advait Parulekar, Liam Collins, Karthikeyan Shanmugam, Aryan Mokhtari, Sanjay Shakkottai

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

FedAvg with Fine Tuning: Local Updates Lead to Representation Learning.

Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

MAML and ANIL Provably Learn Representations.

Liam Collins, Aryan Mokhtari, Sewoong Oh, Sanjay Shakkottai

Proceedings of the International Conference on Machine Learning, 2022

How Does the Task Landscape Affect MAML Performance?

Liam Collins, Aryan Mokhtari, Sanjay Shakkottai

Proceedings of the Conference on Lifelong Learning Agents, 2022

2021

Exploiting Shared Representations for Personalized Federated Learning.

Liam Collins, Hamed Hassani, Aryan Mokhtari, Sanjay Shakkottai

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Why Does MAML Outperform ERM? An Optimization Perspective.

Liam Collins, Aryan Mokhtari, Sanjay Shakkottai

CoRR, 2020

Distribution-Agnostic Model-Agnostic Meta-Learning.

Liam Collins, Aryan Mokhtari, Sanjay Shakkottai

CoRR, 2020

Task-Robust Model-Agnostic Meta-Learning.

Liam Collins, Aryan Mokhtari, Sanjay Shakkottai

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2015

Alaska Steve: Using Virtual Reality to Enhance a 2D Platforming Game.

Liam Collins, Stefan Eylott, John Leedale, T. C. Nicholas Graham

Proceedings of the 2015 Annual Symposium on Computer-Human Interaction in Play, 2015