# Bandit Guided Submodular Curriculum for Adaptive Subset Selection

arXiv: https://arxiv.org/abs/2511.22944 · HTML: https://mlsanity.com/paper/2511.22944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 37 of its 58 references that are in the map.
- First posted on arXiv 28 Nov 2025.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Optimizing Neural Networks with Kronecker-factored Approximate Curvature](https://mlsanity.com/paper/1503.05671/) (2015)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [LESS: Selecting Influential Data for Targeted Instruction Tuning](https://mlsanity.com/paper/2402.04333/) (2024)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Not All Samples Are Created Equal: Deep Learning with Importance Sampling](https://mlsanity.com/paper/1803.00942/) (2018)
- [Empirical Analysis of the Hessian of Over-Parametrized Neural Networks](https://mlsanity.com/paper/1706.04454/) (2017)
- [GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training](https://mlsanity.com/paper/2103.00123/) (2021)
- [Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt](https://mlsanity.com/paper/2206.07137/) (2022)
- [Continual Learning of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2404.16789/) (2024)
- [GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning](https://mlsanity.com/paper/2012.10630/) (2020)
- [Task-Free Continual Learning](https://mlsanity.com/paper/1812.03596/) (2018)
- [Online Batch Selection for Faster Training of Neural Networks](https://mlsanity.com/paper/1511.06343/) (2015)
- [Coverage-centric Coreset Selection for High Pruning Rates](https://mlsanity.com/paper/2210.15809/) (2022)
- [D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning](https://mlsanity.com/paper/2310.07931/) (2023)
- [Restricted Strong Convexity Implies Weak Submodularity](https://mlsanity.com/paper/1612.00804/) (2016)
- [PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection](https://mlsanity.com/paper/2103.00128/) (2021)
- [Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks](https://mlsanity.com/paper/2010.04261/) (2020)
- [Guarantees for Greedy Maximization of Non-submodular Functions with Applications](https://mlsanity.com/paper/1703.02100/) (2017)
- [Gradient Methods for Submodular Maximization](https://mlsanity.com/paper/1708.03949/) (2017)
- [Prioritizing Samples in Reinforcement Learning with Reducible Loss](https://mlsanity.com/paper/2208.10483/) (2022)
- [Curriculum Learning for Small Code Language Models](https://mlsanity.com/paper/2407.10194/) (2024)
- [Sampling from a k-DPP without looking at all items](https://mlsanity.com/paper/2006.16947/) (2020)
- [Data Pruning by Information Maximization](https://mlsanity.com/paper/2506.01701/) (2025)
- [Distributionally Robust Submodular Maximization](https://mlsanity.com/paper/1802.05249/) (2018)

## Abstract (arXiv)

Traditional curriculum learning proceeds from easy to hard samples, yet defining a reliable notion of difficulty remains elusive. Prior work has used submodular functions to induce difficulty scores in curriculum learning. We reinterpret adaptive subset selection and formulate it as a multi-armed bandit problem, where each arm corresponds to a submodular function guiding sample selection. We introduce ONLINESUBMOD, a novel online greedy policy that optimizes a utility-driven reward and provably achieves no-regret performance under various sampling regimes. Empirically, ONLINESUBMOD outperforms both traditional curriculum learning and bi-level optimization approaches across vision and language datasets, showing superior accuracy-efficiency tradeoffs. More broadly, we show that validationdriven reward metrics offer a principled way to guide the curriculum schedule.