# Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees

arXiv: https://arxiv.org/abs/2310.15974 · HTML: https://mlsanity.com/paper/2310.15974/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 24 Oct 2023.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Age Progression/Regression by Conditional Adversarial Autoencoder](https://mlsanity.com/paper/1702.08423/) (2017)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [Reinforced Continual Learning](https://mlsanity.com/paper/1805.12369/) (2018)
- [The CLEAR Benchmark: Continual LEArning on Real-World Imagery](https://mlsanity.com/paper/2201.06289/) (2022)
- [Gradient-based Editing of Memory Examples for Online Task-free Continual Learning](https://mlsanity.com/paper/2006.15294/) (2020)
- [A Century of Portraits: A Visual Historical Record of American High School Yearbooks](https://mlsanity.com/paper/1511.02575/) (2015)
- [Posterior Meta-Replay for Continual Learning](https://mlsanity.com/paper/2103.01133/) (2021)
- [A Minimax Approach to Supervised Learning](https://mlsanity.com/paper/1606.02206/) (2016)
- [On the Reliable Detection of Concept Drift from Streaming Unlabeled Data](https://mlsanity.com/paper/1704.00023/) (2017)
- [Random Feature-based Online Multi-kernel Learning in Environments with Unknown Dynamics](https://mlsanity.com/paper/1712.09983/) (2017)
- [Optimizing Reusable Knowledge for Continual Learning via Metalearning](https://mlsanity.com/paper/2106.05390/) (2021)
- [Handling Concept Drift via Model Reuse](https://mlsanity.com/paper/1809.02804/) (2018)
- [Generalized Maximum Entropy for Supervised Classification](https://mlsanity.com/paper/2007.05447/) (2020)
- [Minimax Classification with 0-1 Loss and Performance Guarantees](https://mlsanity.com/paper/2010.07964/) (2020)
- [The Strength of Nesterov's Extrapolation in the Individual Convergence of Nonsmooth Optimization](https://mlsanity.com/paper/2006.04340/) (2020)
- [Minimax risk classifiers with 0-1 loss](https://mlsanity.com/paper/2201.06487/) (2022)
- [Minimax Classification under Concept Drift with Multidimensional Adaptation and Performance Guarantees](https://mlsanity.com/paper/2205.15942/) (2022)

## Built on by (most cited first, 2 of 2)

- [Reliable Programmatic Weak Supervision with Confidence Intervals for Label Probabilities](https://mlsanity.com/paper/2508.03896/) (2025)
- [IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing](https://mlsanity.com/paper/2609.06131/) (2026)

## Abstract (arXiv)

For a sequence of classification tasks that arrive over time, it is common that tasks are evolving in the sense that consecutive tasks often have a higher similarity. The incremental learning of a growing sequence of tasks holds promise to enable accurate classification even with few samples per task by leveraging information from all the tasks in the sequence (forward and backward learning). However, existing techniques developed for continual learning and concept drift adaptation are either designed for tasks with time-independent similarities or only aim to learn the last task in the sequence. This paper presents incremental minimax risk classifiers (IMRCs) that effectively exploit forward and backward learning and account for evolving tasks. In addition, we analytically characterize the performance improvement provided by forward and backward learning in terms of the tasks' expected quadratic change and the number of tasks. The experimental evaluation shows that IMRCs can result in a significant performance improvement, especially for reduced sample sizes.