Zobrazeno 1 - 10
of 4 768
pro vyhledávání: '"P Gower"'
Slow relaxation and glassiness have been the focus of extensive research attention, along with popular and technological interest, for many decades. While much understanding has been attained through mean-field and mode-coupling models, energy landsc
Externí odkaz:
http://arxiv.org/abs/2410.14552
Recent advances in implicit neural representation (INR)-based video coding have demonstrated its potential to compete with both conventional and other learning-based approaches. With INR methods, a neural network is trained to overfit a video sequenc
Externí odkaz:
http://arxiv.org/abs/2409.07414
Autor:
Tiukova, Ievgeniia A., Brunnsåker, Daniel, Bjurström, Erik Y., Gower, Alexander H., Kronström, Filip, Reder, Gabriel K., Reiserer, Ronald S., Korovin, Konstantin, Soldatova, Larisa B., Wikswo, John P., King, Ross D.
The cutting edge of applying AI to science is the closed-loop automation of scientific research: robot scientists. We have previously developed two robot scientists: `Adam' (for yeast functional biology), and `Eve' (for early-stage drug design)). We
Externí odkaz:
http://arxiv.org/abs/2408.10689
Particulate materials include powders, emulsions, composites, and many others. This is why measuring these has become important for both industry and scientific applications. For industrial applications, the greatest need is to measure dense particul
Externí odkaz:
http://arxiv.org/abs/2407.07032
Autor:
Gower, Alexander H., Korovin, Konstantin, Brunnsåker, Daniel, Kronström, Filip, Reder, Gabriel K., Tiukova, Ievgeniia A., Reiserer, Ronald S., Wikswo, John P., King, Ross D.
The process of developing theories and models and testing them with experiments is fundamental to the scientific method. Automating the entire scientific method then requires not only automation of the induction of theories from data, but also experi
Externí odkaz:
http://arxiv.org/abs/2406.17835
Autor:
Li, Yunxiang, Yuan, Rui, Fan, Chen, Schmidt, Mark, Horváth, Samuel, Gower, Robert M., Takáč, Martin
Policy gradient is a widely utilized and foundational algorithm in the field of reinforcement learning (RL). Renowned for its convergence guarantees and stability compared to other RL algorithms, its practical application is often hindered by sensiti
Externí odkaz:
http://arxiv.org/abs/2404.07525
A large variety of materials, widely encountered both in engineering applications and in the biological realm, are characterised by a non-vanishing internal stress distribution, even in the absence of external deformations or applied forces. These in
Externí odkaz:
http://arxiv.org/abs/2403.09280
We develop new sub-optimality bounds for gradient descent (GD) that depend on the conditioning of the objective along the path of optimization, rather than on global, worst-case constants. Key to our proofs is directional smoothness, a measure of gra
Externí odkaz:
http://arxiv.org/abs/2403.04081
We study level set teleportation, an optimization sub-routine which seeks to accelerate gradient methods by maximizing the gradient norm on a level-set of the objective function. Since the descent lemma implies that gradient descent (GD) decreases th
Externí odkaz:
http://arxiv.org/abs/2403.03362
Autor:
Cai, Diana, Modi, Chirag, Pillaud-Vivien, Loucas, Margossian, Charles C., Gower, Robert M., Blei, David M., Saul, Lawrence K.
Most leading implementations of black-box variational inference (BBVI) are based on optimizing a stochastic evidence lower bound (ELBO). But such approaches to BBVI often converge slowly due to the high variance of their gradient estimates and their
Externí odkaz:
http://arxiv.org/abs/2402.14758