activity
20182021
most citedMaking learning more transparent using conformalized performance prediction

4 citations · 10 across the 4 of their papers we have counts for

collaborators

10 papers

stat.ML2021

Spectral risk-based learning using unbounded losses

Matthew J. Holland, El Mehdi Haress

In this work, we consider the setting of learning problems under a wide class of spectral risk (or "L-risk") functions, where a Lipschitz-continuous spectral density is used to fle…

stat.ML2020

Better scalability under potentially heavy-tailed feedback

Matthew J. Holland

We study scalable alternatives to robust gradient descent (RGD) techniques that can be used when the losses and/or gradients can be heavy-tailed, though this will be unknown to the…

stat.ML20204 cited

Making learning more transparent using conformalized performance prediction

Matthew J. Holland

In this work, we study some novel applications of conformal inference techniques to the problem of providing machine learning procedures with more transparent, accurate, and practi…

stat.ML20202 cited

Learning with CVaR-based feedback under potentially heavy tails

Matthew J. Holland, El Mehdi Haress

We study learning algorithms that seek to minimize the conditional value-at-risk (CVaR), when all the learner knows is that the losses incurred may be heavy-tailed. We begin by stu…

stat.ML2020

Improved scalability under heavy tails, without strong convexity

Matthew J. Holland

Real-world data is laden with outlying values. The challenge for machine learning is that the learner typically has no prior knowledge of whether the feedback it receives (losses,…

stat.ML2020

Better scalability under potentially heavy-tailed gradients

Matthew J. Holland

We study a scalable alternative to robust gradient descent (RGD) techniques that can be used when the gradients can be heavy-tailed, though this will be unknown to the learner. The…