Zobrazeno 1 - 10
of 174
pro vyhledávání: '"Lau, Tim"'
Modern deep neural networks often require distributed training with many workers due to their large size. As worker numbers increase, communication overheads become the main bottleneck in data-parallel minibatch stochastic gradient methods with per-i
Externí odkaz:
http://arxiv.org/abs/2406.13936
The choice of batch sizes in minibatch stochastic gradient optimizers is critical in large-scale model training for both optimization and generalization performance. Although large-batch training is arguably the dominant training paradigm for large-s
Externí odkaz:
http://arxiv.org/abs/2402.11215
We study the problem of approximate sampling from non-log-concave distributions, e.g., Gaussian mixtures, which is often challenging even in low dimensions due to their multimodality. We focus on performing this task via Markov chain Monte Carlo (MCM
Externí odkaz:
http://arxiv.org/abs/2305.15988
Autor:
Lau, Tim Tsz-Kit, Liu, Han
We propose efficient Langevin Monte Carlo algorithms for sampling distributions with nonsmooth convex composite potentials, which is the sum of a continuously differentiable function and a possibly nonsmooth function. We devise such algorithms levera
Externí odkaz:
http://arxiv.org/abs/2207.04387
Autor:
Lau, Tim Tsz-Kit, Liu, Han
In many applications in statistics and machine learning, the availability of data samples from multiple possibly heterogeneous sources has become increasingly prevalent. On the other hand, in distributionally robust optimization, we seek data-driven
Externí odkaz:
http://arxiv.org/abs/2203.12136
Autor:
Lau, Tim Tsz-Kit, Sengupta, Biswa
We study two state-of-the-art solutions to the multi-agent pickup and delivery (MAPD) problem based on different principles -- multi-agent path-finding (MAPF) and multi-agent reinforcement learning (MARL). Specifically, a recent MAPF algorithm called
Externí odkaz:
http://arxiv.org/abs/2203.07092
Autor:
Liu, Hengrui, Salehi, Fatemeh, Abbassi, Rouzbeh, Lau, Tim, Heng Yeoh, Guan, Mitchell-Corbett, Fiona, Raman, Venkat
Publikováno v:
In Journal of Loss Prevention in the Process Industries December 2023 86
Publikováno v:
In Exploratory Research in Clinical and Social Pharmacy March 2023 9
Training deep neural networks (DNNs) efficiently is a challenge due to the associated highly nonconvex optimization. The backpropagation (backprop) algorithm has long been the most widely used algorithm for gradient computation of parameters of DNNs
Externí odkaz:
http://arxiv.org/abs/1803.09082
Publikováno v:
Proceeding of the 36th International Conference on Machine Learning (ICML), 2019
Deep learning has aroused extensive attention due to its great empirical success. The efficiency of the block coordinate descent (BCD) methods has been recently demonstrated in deep neural network (DNN) training. However, theoretical studies on their
Externí odkaz:
http://arxiv.org/abs/1803.00225