Computer Science: Recent submissions
Now showing items 31-35 of 807
-
On suppressing range of adaptive stepsizes of Adam to improve generalisation performance
(Springer, 22 August 2024)A number of recent adaptive optimizers improve the generalisation performance of Adam by essentially reducing the variance of adaptive stepsizes to make a bridge with SGD with momentum. Following the above motivation, we ... -
Exact diffusion inversion via bi-directional integration approximation
(Springer, 2024)Recently, various methods have been proposed to address the inconsistency issue of DDIM inversion to enable image editing, such as EDICT [36] and Null-text inversion [22]. However, the above methods introduce considerable ... -
Distributed Optimisation With Linear Equality and Inequality Constraints Using PDMM
(Institute of Electrical and Electronics Engineers (IEEE), 11 March 2024)In this article, we consider the problem of distributed optimisation of a separable convex cost function over a graph, where every edge and node in the graph could carry both linear equality and/or inequality constraints. ... -
A DNN Optimizer that Improves over AdaBelief by Suppression of the Adaptive Stepsize Range
(Journal of Machine Learning Research Inc., 5 September 2023)We make contributions towards improving adaptive-optimizer performance. Our improvements are based on suppression of the range of adaptive stepsizes in the AdaBelief optimizer. Firstly, we show that the particular placement ... -
On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation
(International Conference on Learning Representations (ICLR), 8 May 2024)A popular approach to sample a diffusion-based generative model is to solve an ordinary differential equation (ODE). In existing samplers, the coefficients of the ODE solvers are pre-determined by the ODE formulation, ...