Related papers: Immediate Derivatives Suffice for Online Recurrent…

We design learning rate schedules that minimize regret for SGD-based online learning in the presence of a changing data distribution. We fully characterize the optimal learning rate schedule for online linear regression via a novel analysis…

Class-incremental learning (CIL) with Vision Transformers (ViTs) faces a major computational bottleneck during the classifier reconstruction phase, where most existing methods rely on costly iterative stochastic gradient descent (SGD). We…

The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches. A deep continual learning algorithm, namely…

Deep neural networks are the most commonly used function approximators in offline reinforcement learning. Prior works have shown that neural nets trained with TD-learning and gradient descent can exhibit implicit regularization that can be…

Transformers excel at in-context learning (ICL) -- learning from demonstrations without parameter updates -- but how they do so remains a mystery. Recent work suggests that Transformers may internally run Gradient Descent (GD), a…

This paper studies machine learning-assisted maximum likelihood (ML) and maximum a posteriori (MAP) receivers for a communication system with memory, which can be modelled by a trellis diagram. The prerequisite of the ML/MAP receiver is to…

Online continual learning (OCL) refers to the ability of a system to learn over time from a continuous stream of data without having to revisit previously encountered training samples. Learning continually in a single data pass is crucial…

Deep learning experiments by Cohen et al. [2021] using deterministic Gradient Descent (GD) revealed an Edge of Stability (EoS) phase when learning rate (LR) and sharpness (i.e., the largest eigenvalue of Hessian) no longer behave as in…

Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust to the new data. This need can be adequately addressed by…

Dynamic radio resource management (RRM) in wireless networks presents significant challenges, particularly in the context of Radio Access Network (RAN) slicing. This technology, crucial for catering to varying user requirements, often…

Optimal-Transport Distributionally Robust Optimization (OT-DRO) robustifies data-driven decision-making under uncertainty by capturing the sampling-induced statistical error via optimal transport ambiguity sets. The standard OT-DRO pipeline…

Modern convolutional networks, incorporating rectifiers and max-pooling, are neither smooth nor convex; standard guarantees therefore do not apply. Nevertheless, methods from convex optimization such as gradient descent and Adam are widely…

Temporal action localization requires both precise boundary detection and computational efficiency. Current methods apply uniform computation across all temporal positions, wasting resources on easy boundaries while struggling with…

We devise a distributional variant of gradient temporal-difference (TD) learning. Distributional reinforcement learning has been demonstrated to outperform the regular one in the recent study \citep{bellemare2017distributional}. In the…

Online quantum state learning is a recently proposed problem by Aaronson et al. (2018), where the learner sequentially predicts $n$-qubit quantum states based on given measurements on states and noisy outcomes. In the previous work, the…

Despite the growing success of deep learning (DL) in offline brain-computer interfaces (BCIs), its adoption in real-time applications remains limited due to three primary challenges. First, most DL solutions are designed for offline…

One of the most influential results in neural network theory is the universal approximation theorem [1, 2, 3] which states that continuous functions can be approximated to within arbitrary accuracy by single-hidden-layer feedforward neural…

One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids…

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

Offline-to-Online Reinforcement Learning (O2O RL) faces a critical dilemma in balancing the use of a fixed offline dataset with newly collected online experiences. Standard methods, often relying on a fixed data-mixing ratio, struggle to…