Abstract Machine Learning (ML) models are ubiquitous in real-world applications and are a constant focus of research. Modern ML models have become more complex, deeper, and …
We present a method to formulate algorithm discovery as program search, and apply it to discover optimization algorithms for deep neural network training. We leverage efficient …
Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes …
Realizing quantum speedup for practically relevant, computationally hard problems is a central challenge in quantum information science. Using Rydberg atom arrays with up to …
D Kimanius, L Dong, G Sharov, T Nakane… - Biochemical …, 2021 - portlandpress.com
We describe new tools for the processing of electron cryo-microscopy (cryo-EM) images in the fourth major release of the RELION software. In particular, we introduce VDAM, a …
Motivated by the striking ability of transformers for in-context learning, several works demonstrate that transformers can implement algorithms like gradient descent. By a careful …
Federated learning is an emerging distributed machine learning framework for privacy preservation. However, models trained in federated learning usually have worse …
We present the application of a class of deep learning, known as Physics Informed Neural Networks (PINN), to inversion and surrogate modeling in solid mechanics. We explain how …
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy …