Interactive Machine Learning: From Theory to Scale

• URL: http://arxiv.org/abs/2512.23924v1
• Date: Tue, 30 Dec 2025 00:49:52 GMT
• Title: Interactive Machine Learning: From Theory to Scale
• Authors: Yinglun Zhu,
• Abstract summary: This dissertation studies interactive machine learning, in which the learner actively influences how information is collected or which actions are taken.<n>We develop new algorithmic principles and establish fundamental limits for interactive learning along three dimensions.
• Score: 12.234169944475537
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine learning has achieved remarkable success across a wide range of applications, yet many of its most effective methods rely on access to large amounts of labeled data or extensive online interaction. In practice, acquiring high-quality labels and making decisions through trial-and-error can be expensive, time-consuming, or risky, particularly in large-scale or high-stakes settings. This dissertation studies interactive machine learning, in which the learner actively influences how information is collected or which actions are taken, using past observations to guide future interactions. We develop new algorithmic principles and establish fundamental limits for interactive learning along three dimensions: active learning with noisy data and rich model classes, sequential decision making with large action spaces, and model selection under partial feedback. Our results include the first computationally efficient active learning algorithms achieving exponential label savings without low-noise assumptions; the first efficient, general-purpose contextual bandit algorithms whose guarantees are independent of the size of the action space; and the first tight characterizations of the fundamental cost of model selection in sequential decision making. Overall, this dissertation advances the theoretical foundations of interactive learning by developing algorithms that are statistically optimal and computationally efficient, while also providing principled guidance for deploying interactive learning methods in large-scale, real-world settings.

Related papers

• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• A Human-Centered Approach for Improving Supervised Learning [0.44378250612683995]
  This paper shows how we can strike a balance between performance, time, and resource constraints. Another goal of this research is to make Ensembles more explainable and intelligible using the Human-Centered approach.
  arXiv  Detail & Related papers  (2024-10-14T10:27:14Z)
• Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions [3.0539022029583953]
  This thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. We investigate data subset selection techniques, specifically active learning and active sampling, grounded in information-theoretic principles.
  arXiv  Detail & Related papers  (2024-01-09T01:41:36Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Learning to Rank for Active Learning via Multi-Task Bilevel Optimization [29.207101107965563]
  We propose a novel approach for active learning, which aims to select batches of unlabeled instances through a learned surrogate model for data acquisition. A key challenge in this approach is developing an acquisition function that generalizes well, as the history of data, which forms part of the utility function's input, grows over time.
  arXiv  Detail & Related papers  (2023-10-25T22:50:09Z)
• PILOT: A Pre-Trained Model-Based Continual Learning Toolbox [65.57123249246358]
  This paper introduces a pre-trained model-based continual learning toolbox known as PILOT.<n>On the one hand, PILOT implements some state-of-the-art class-incremental learning algorithms based on pre-trained models, such as L2P, DualPrompt, and CODA-Prompt.<n>On the other hand, PILOT fits typical class-incremental learning algorithms within the context of pre-trained models to evaluate their effectiveness.
  arXiv  Detail & Related papers  (2023-09-13T17:55:11Z)
• Responsible Active Learning via Human-in-the-loop Peer Study [88.01358655203441]
  We propose a responsible active learning method, namely Peer Study Learning (PSL), to simultaneously preserve data privacy and improve model stability. We first introduce a human-in-the-loop teacher-student architecture to isolate unlabelled data from the task learner (teacher) on the cloud-side. During training, the task learner instructs the light-weight active learner which then provides feedback on the active sampling criterion.
  arXiv  Detail & Related papers  (2022-11-24T13:18:27Z)
• What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks? [59.51457877578138]
  We study contrastive learning on the wearable-based activity recognition task. This paper presents an open-source PyTorch library textttCL-HAR, which can serve as a practical tool for researchers.
  arXiv  Detail & Related papers  (2022-02-12T06:10:15Z)
• The Statistical Complexity of Interactive Decision Making [126.04974881555094]
  We provide a complexity measure, the Decision-Estimation Coefficient, that is proven to be both necessary and sufficient for sample-efficient interactive learning. A unified algorithm design principle, Estimation-to-Decisions (E2D), transforms any algorithm for supervised estimation into an online algorithm for decision making.
  arXiv  Detail & Related papers  (2021-12-27T02:53:44Z)
• Clustering Analysis of Interactive Learning Activities Based on Improved BIRCH Algorithm [0.0]
  The construction of good learning behavior is of great significance to learners' learning process and learning effect, and is the key basis of data-driven education decision-making. It is necessary to obtain the online learning behavior big data set of multi period and multi course, and describe the learning behavior as multi-dimensional learning interaction activities. We design an improved algorithm of BIRCH clustering based on random walking strategy, which realizes the retrieval evaluation and data of key learning interaction activities.
  arXiv  Detail & Related papers  (2020-10-08T07:46:46Z)
• Learning High Order Feature Interactions with Fine Control Kernels [12.5433010409486]
  We provide a methodology for learning sparse statistical models that use as features all possible multiplicative interactions. We also introduce an algorithmic paradigm, the Fine Control Kernel framework, so named because it is based on Fenchel Duality.
  arXiv  Detail & Related papers  (2020-02-09T06:29:15Z)

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.