activity
20182022
most citedMEMe: An Accurate Maximum Entropy Method for Efficient Approximations in Large-Scale Machine Learning

21 citations · 63 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2022

Learning to Identify Top Elo Ratings: A Dueling Bandits Approach

Xue Yan, Yali Du, Binxin Ru +3

The Elo rating system is widely adopted to evaluate the skills of (chess) game and sports players. Recently it has been also integrated into machine learning algorithms in evaluati…

cs.LG2021

Approximate Neural Architecture Search via Operation Distribution Learning

Xingchen Wan, Binxin Ru, Pedro M. Esperança +1

The standard paradigm in Neural Architecture Search (NAS) is to search for a fully deterministic architecture with specific operations and connections. In this work, we instead pro…

cs.LG2021

AUTOKD: Automatic Knowledge Distillation Into A Student Architecture Family

Roy Henha Eyono, Fabio Maria Carlucci, Pedro M Esperança +2

State-of-the-art results in deep learning have been improving steadily, in good part due to the use of larger models. However, widespread use is constrained by device hardware limi…

cs.LG2021

How Powerful are Performance Predictors in Neural Architecture Search?

Colin White, Arber Zela, Binxin Ru +2

Early methods in the rapidly developing field of neural architecture search (NAS) required fully training thousands of neural networks. To reduce this extreme computational cost, d…

cs.LG20209 cited

A Bayesian Perspective on Training Speed and Model Selection

Clare Lyle, Lisa Schut, Binxin Ru +2

We take a Bayesian perspective to illustrate a connection between training speed and the marginal likelihood in linear models. This provides two major insights: first, that a measu…

cs.LG2020

Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels

Binxin Ru, Xingchen Wan, Xiaowen Dong +1

Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or…