Risk regularization through bidirectional dispersion
- URL: http://arxiv.org/abs/2203.14434v1
- Date: Mon, 28 Mar 2022 01:13:44 GMT
- Title: Risk regularization through bidirectional dispersion
- Authors: Matthew J. Holland
- Abstract summary: Many alternative notions of "risk" are at least as sensitive as the mean to loss tails on the upside, and tend to ignore deviations on the downside.
In this work, we study a complementary new risk class that penalizes loss deviations in a bidirectional manner.
- Score: 9.36599317326032
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Many alternative notions of "risk" (e.g., CVaR, entropic 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 upside, and tend to ignore deviations on the
downside. In this work, we study a complementary new risk class that penalizes
loss deviations in a bidirectional manner, while having more flexibility in
terms of tail sensitivity than is offered by classical mean-variance, without
sacrificing computational or analytical tractability.
Related papers
- Data-Adaptive Tradeoffs among Multiple Risks in Distribution-Free Prediction [55.77015419028725]
We develop methods that permit valid control of risk when threshold and tradeoff parameters are chosen adaptively.
Our methodology supports monotone and nearly-monotone risks, but otherwise makes no distributional assumptions.
arXiv Detail & Related papers (2024-03-28T17:28:06Z) - Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning.
We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values.
We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
arXiv Detail & Related papers (2023-12-07T15:55:58Z) - An Alternative to Variance: Gini Deviation for Risk-averse Policy
Gradient [35.01235012813407]
Restricting the variance of a policy's return is a popular choice in risk-averse Reinforcement Learning.
Recent methods restrict the per-step reward variance as a proxy.
We propose to use an alternative risk measure, Gini deviation, as a substitute.
arXiv Detail & Related papers (2023-07-17T22:08:27Z) - Prediction Risk and Estimation Risk of the Ridgeless Least Squares Estimator under General Assumptions on Regression Errors [10.857775300638831]
We explore prediction risk as well as estimation risk under more general regression error assumptions.
Our findings suggest that the benefits of over parameterization can extend to time series, panel and grouped data.
arXiv Detail & Related papers (2023-05-22T10:04:20Z) - One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based
Offline Reinforcement Learning [25.218430053391884]
We propose risk-sensitivity as a mechanism to jointly address both of these issues.
Risk-aversion to aleatoric uncertainty discourages actions that may result in poor outcomes due to environmentity.
Our experiments show that our algorithm achieves competitive performance on deterministic benchmarks.
arXiv Detail & Related papers (2022-11-30T21:24:11Z) - Efficient Risk-Averse Reinforcement Learning [79.61412643761034]
In risk-averse reinforcement learning (RL), the goal is to optimize some risk measure of the returns.
We prove that under certain conditions this inevitably leads to a local-optimum barrier, and propose a soft risk mechanism to bypass it.
We demonstrate improved risk aversion in maze navigation, autonomous driving, and resource allocation benchmarks.
arXiv Detail & Related papers (2022-05-10T19:40:52Z) - A Manifold View of Adversarial Risk [23.011667845523267]
We investigate two new types of adversarial risk, the normal adversarial risk due to perturbation along normal direction, and the in-manifold adversarial risk due to perturbation within the manifold.
We show with a surprisingly pessimistic case that the standard adversarial risk can be nonzero even when both normal and in-manifold risks are zero.
arXiv Detail & Related papers (2022-03-24T18:11:21Z) - PAC$^m$-Bayes: Narrowing the Empirical Risk Gap in the Misspecified
Bayesian Regime [75.19403612525811]
This work develops a multi-sample loss which can close the gap by spanning a trade-off between the two risks.
Empirical study demonstrates improvement to the predictive distribution.
arXiv Detail & Related papers (2020-10-19T16:08:34Z) - The Risks of Invariant Risk Minimization [52.7137956951533]
Invariant Risk Minimization is an objective based on the idea for learning deep, invariant features of data.
We present the first analysis of classification under the IRM objective--as well as these recently proposed alternatives--under a fairly natural and general model.
We show that IRM can fail catastrophically unless the test data are sufficiently similar to the training distribution--this is precisely the issue that it was intended to solve.
arXiv Detail & Related papers (2020-10-12T14:54:32Z) - Learning Bounds for Risk-sensitive Learning [86.50262971918276]
In risk-sensitive learning, one aims to find a hypothesis that minimizes a risk-averse (or risk-seeking) measure of loss.
We study the generalization properties of risk-sensitive learning schemes whose optimand is described via optimized certainty equivalents.
arXiv Detail & Related papers (2020-06-15T05:25:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.