Related papers: Low-Regret and Low-Complexity Learning for Hierarc…

Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical setting. Our…

Large Language Models (LLMs) have demonstrated remarkable abilities in various language tasks, making them promising candidates for decision-making in robotics. Inspired by Hierarchical Reinforcement Learning (HRL), we propose…

We consider the setting of online logistic regression and consider the regret with respect to the 2-ball of radius B. It is known (see [Hazan et al., 2014]) that any proper algorithm which has logarithmic regret in the number of samples…

We propose a novel framework and a solution to tackle the continual learning (CL) problem with changing network architectures. Most CL methods focus on adapting a single architecture to a new task/class by modifying its weights. However,…

Hamilton-Jacobi (HJ) reachability provides formal safety guarantees for nonlinear systems. However, it becomes computationally intractable in high-dimensional settings, motivating learning-based approximations that may introduce unsafe…

In Iterative Learning Control (ILC), a sequence of feedforward control actions is generated at each iteration on the basis of partial model knowledge and past measurements with the goal of steering the system toward a desired reference…

Transformers have demonstrated exceptional in-context learning (ICL) capabilities, enabling applications across natural language processing, computer vision, and sequential decision-making. In reinforcement learning, ICL reframes learning…

While existing hierarchical text classification (HTC) methods attempt to capture label hierarchies for model training, they either make local decisions regarding each label or completely ignore the hierarchy information during inference. To…

Emerging cyber-physical systems increasingly require low-latency inference from streaming sensor data while maintaining models that reflect complex and evolving physical processes. In many domains, however, model updates depend on…

Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these…

AI-powered edge devices currently lack the ability to adapt their embedded inference models to the ever-changing environment. To tackle this issue, Continual Learning (CL) strategies aim at incrementally improving the decision capabilities…

Online learning aims to perform nearly as well as the best hypothesis in hindsight. For some hypothesis classes, though, even finding the best hypothesis offline is challenging. In such offline cases, local search techniques are often…

The use of lightweight machine learning (ML) models in internet of things (IoT) networks enables resource constrained IoT devices to perform on-device inference for several critical applications. However, the inference accuracy deteriorates…

Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon planning, and settings with sparse rewards. However, learning…

Motivated by the episodic version of the classical inventory control problem, we propose a new Q-learning-based algorithm, Elimination-Based Half-Q-Learning (HQL), that enjoys improved efficiency over existing algorithms for a wide variety…

Knowledge Tracing (KT) aims to mine students' evolving knowledge states and predict their future question-answering performance. Existing methods based on heterogeneous information networks (HINs) are prone to introducing noises due to…

We study the problem of oracle-efficient hybrid online learning when the features are generated by an unknown i.i.d. process and the labels are generated adversarially. Assuming access to an (offline) ERM oracle, we show that there exists a…

In various control task domains, existing controllers provide a baseline level of performance that -- though possibly suboptimal -- should be maintained. Reinforcement learning (RL) algorithms that rely on extensive exploration of the state…

Hierarchical reinforcement learning (HRL) holds great potential for sample-efficient learning on challenging long-horizon tasks. In particular, letting a higher level assign subgoals to a lower level has been shown to enable fast learning…

Emerging mobility systems are increasingly capable of recommending options to mobility users, to guide them towards personalized yet sustainable system outcomes. Even more so than the typical recommendation system, it is crucial to minimize…