# Risk-averse learning with delayed feedback

arXiv: https://arxiv.org/abs/2409.16866 · HTML: https://mlsanity.com/paper/2409.16866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 25 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [Non-stationary Stochastic Optimization](https://mlsanity.com/paper/1307.5449/) (2013)
- [Online Learning under Delayed Feedback](https://mlsanity.com/paper/1306.0686/) (2013)
- [An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback](https://mlsanity.com/paper/1507.08752/) (2015)
- [Optimizing the CVaR via Sampling](https://mlsanity.com/paper/1404.3862/) (2014)
- [Efficient Risk-Averse Reinforcement Learning](https://mlsanity.com/paper/2205.05138/) (2022)
- [Bandit Convex Optimization in Non-stationary Environments](https://mlsanity.com/paper/1907.12340/) (2019)
- [Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments](https://mlsanity.com/paper/2204.08281/) (2022)
- [Delayed Feedback in Generalised Linear Bandits Revisited](https://mlsanity.com/paper/2207.10786/) (2022)
- [Bandit Online Learning with Unknown Delays](https://mlsanity.com/paper/1807.03205/) (2018)
- [A New One-Point Residual-Feedback Oracle For Black-Box Learning and Control](https://mlsanity.com/paper/2006.10820/) (2020)
- [Risk-Averse Stochastic Convex Bandit](https://mlsanity.com/paper/1810.00737/) (2018)
- [A Zeroth-Order Momentum Method for Risk-Averse Online Convex Games](https://mlsanity.com/paper/2209.02838/) (2022)
- [Non-stationary Delayed Online Convex Optimization: From Full-information to Bandit Setting](https://mlsanity.com/paper/2305.12131/) (2023)
- [Delay-Tolerant Constrained OCO with Application to Network Resource Allocation](https://mlsanity.com/paper/2105.04005/) (2021)

## Abstract (arXiv)

In real-world scenarios, risk-averse learning is valuable for mitigating potential adverse outcomes. However, the delayed feedback makes it challenging to assess and manage risk effectively. In this paper, we investigate risk-averse learning using Conditional Value at Risk (CVaR) as risk measure, while incorporating feedback with random but bounded delays. We develop two risk-averse learning algorithms that rely on one-point and two-point zeroth-order optimization approaches, respectively. The dynamic regrets of the algorithms are analyzed in terms of the cumulative delay and the number of total samplings. In the absence of delay, the regret bounds match the established bounds of zeroth-order stochastic gradient methods for risk-averse learning. Furthermore, the two-point risk-averse learning outperforms the one-point algorithm by achieving a smaller regret bound. We provide numerical experiments on a dynamic pricing problem to demonstrate the performance of the algorithms.