19 citations · 59 across the 16 of their papers we have counts for
16 papers
Robust variance-regularized risk minimization with concomitant scaling
Matthew J. Holland
Under losses which are potentially heavy-tailed, we consider the task of minimizing sums of the loss mean and standard deviation, without trying to accurately estimate the variance…
Flexible risk design using bi-directional dispersion
Matthew J. Holland
Many novel notions of "risk" (e.g., CVaR, tilted risk, DRO risk) have been proposed and studied, but these risks are all at least as sensitive as the mean to loss tails on the upsi…
A Survey of Learning Criteria Going Beyond the Usual Risk
Matthew J. Holland, Kazuki Tanabe
Virtually all machine learning tasks are characterized using some form of loss function, and "good performance" is typically stated in terms of a sufficiently small average loss, t…
Robust learning with anytime-guaranteed feedback
Matthew J. Holland
Under data distributions which may be heavy-tailed, many stochastic gradient-based learning algorithms are driven by feedback queried at points with almost no performance guarantee…
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…
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…
Learning with risks based on M-location
Matthew J. Holland
In this work, we study a new class of risks defined in terms of the location and deviation of the loss distribution, generalizing far beyond classical mean-variance risk functions.…
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…
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…
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,…
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…
Distribution-robust mean estimation via smoothed random perturbations
Matthew J. Holland
We consider the problem of mean estimation assuming only finite variance. We study a new class of mean estimators constructed by integrating over random noise applied to a soft-tru…
PAC-Bayes under potentially heavy tails
Matthew J. Holland
We derive PAC-Bayesian learning guarantees for heavy-tailed losses, and obtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds at logarithmic confiden…
Robust descent using smoothed multiplicative noise
Matthew J. Holland
To improve the off-sample generalization of classical procedures minimizing the empirical risk under potentially heavy-tailed data, new robust learning algorithms have been propose…
Classification using margin pursuit
Matthew J. Holland
In this work, we study a new approach to optimizing the margin distribution realized by binary classifiers. The classical approach to this problem is simply maximization of the exp…
Efficient learning with robust gradient descent
Matthew J. Holland, Kazushi Ikeda
Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to gene…