Online learning holds the promise of enabling efficient long-term credit assignment in recurrent neural networks. However, current algorithms fall short of offline backpropagation by either not being scalable or failing to learn long-range dependencies. Here we present a high-performance online learning algorithm that merely doubles the memory and computational requirements of a single inference pass. We achieve this by leveraging independent recurrent modules in multi-layer networks, an architectural motif that has recently been shown to be particularly powerful. Experiments on synthetic memory problems and on the challenging long-range arena benchmark suite reveal that our algorithm performs competitively, establishing a new standard for what can be achieved through online learning. This ability to learn long-range dependencies offers a new perspective on learning in the brain and opens a promising avenue in neuromorphic computing.

Online learning quantum states with the logarithmic loss (LL-OLQS) is a quantum generalization of online portfolio selection, a classic open problem in the field of online learning for over three decades. The problem also emerges in designing randomized optimization algorithms for maximum-likelihood quantum state tomography. Recently, Jezequel et al. (arXiv:2209.13932) proposed the VB-FTRL algorithm, the first nearly regret-optimal algorithm for OPS with moderate computational complexity. In this note, we generalize VB-FTRL for LL-OLQS. Let $d$ denote the dimension and $T$ the number of rounds. The generalized algorithm achieves a regret rate of $O ( d^2 \log ( d + T ) )$ for LL-OLQS. Each iteration of the algorithm consists of solving a semidefinite program that can be implemented in polynomial time by, e.g., cutting-plane methods. For comparison, the best-known regret rate for LL-OLQS is currently $O ( d^2 \log T )$, achieved by the exponential weight method. However, there is no explicit implementation available for the exponential weight method for LL-OLQS. To facilitate the generalization, we introduce the notion of VB-convexity. VB-convexity is a sufficient condition for the logarithmic barrier associated with any function to be convex and is of independent interest.

Contextual bandits (Auer, 2002; Langford and Zhang, 2007) represent a classical sequential decisionmaking problem where an agent aims to maximize cumulative reward based on context information. At each round t, the agent observes a context and must choose one of K available actions based on both the current context and previous observations. Once the agent selects an action, she observes the associated reward, which is then used to refine future decision-making. Contextual bandits are typical examples of reinforcement learning problems where a balance between exploring new actions and exploiting previously acquired information is necessary to achieve optimal long-term rewards. It has numerous real-world applications including personalized recommendation systems (Li et al., 2010; Bouneffouf et al., 2012), healthcare (Yom-Tov et al., 2017; Liao et al., 2020), and online education (Liu et al., 2014; Shaikh et al., 2019). Despite the extensive existing literature on contextual bandits, in many real-world applications, the agent never observes the context exactly.

Distributed online learning has been proven extremely effective in solving large-scale machine learning problems over streaming data. However, information sharing between learners in distributed learning also raises concerns about the potential leakage of individual learners' sensitive data. To mitigate this risk, differential privacy, which is widely regarded as the "gold standard" for privacy protection, has been widely employed in many existing results on distributed online learning. However, these results often face a fundamental tradeoff between learning accuracy and privacy. In this paper, we propose a locally differentially private gradient tracking based distributed online learning algorithm that successfully circumvents this tradeoff. We prove that the proposed algorithm converges in mean square to the exact optimal solution while ensuring rigorous local differential privacy, with the cumulative privacy budget guaranteed to be finite even when the number of iterations tends to infinity. The algorithm is applicable even when the communication graph among learners is directed. To the best of our knowledge, this is the first result that simultaneously ensures learning accuracy and rigorous local differential privacy in distributed online learning over directed graphs. We evaluate our algorithm's performance by using multiple benchmark machine-learning applications, including logistic regression of the "Mushrooms" dataset and CNN-based image classification of the "MNIST" and "CIFAR-10" datasets, respectively. The experimental results confirm that the proposed algorithm outperforms existing counterparts in both training and testing accuracies.

In this work, we aim to characterize the statistical complexity of realizable regression both in the PAC learning setting and the online learning setting. Previous work had established the sufficiency of finiteness of the fat shattering dimension for PAC learnability and the necessity of finiteness of the scaled Natarajan dimension, but little progress had been made towards a more complete characterization since the work of Simon (SICOMP '97). To this end, we first introduce a minimax instance optimal learner for realizable regression and propose a novel dimension that both qualitatively and quantitatively characterizes which classes of real-valued predictors are learnable. We then identify a combinatorial dimension related to the Graph dimension that characterizes ERM learnability in the realizable setting. Finally, we establish a necessary condition for learnability based on a combinatorial dimension related to the DS dimension, and conjecture that it may also be sufficient in this context. Additionally, in the context of online learning we provide a dimension that characterizes the minimax instance optimal cumulative loss up to a constant factor and design an optimal online learner for realizable regression, thus resolving an open question raised by Daskalakis and Golowich in STOC '22.

In this work, we improve on the upper and lower bounds for the regret of online learning with strongly observable undirected feedback graphs. The best known upper bound for this problem is $\mathcal{O}\bigl(\sqrt{\alpha T\ln K}\bigr)$, where $K$ is the number of actions, $\alpha$ is the independence number of the graph, and $T$ is the time horizon. The $\sqrt{\ln K}$ factor is known to be necessary when $\alpha = 1$ (the experts case). On the other hand, when $\alpha = K$ (the bandits case), the minimax rate is known to be $\Theta\bigl(\sqrt{KT}\bigr)$, and a lower bound $\Omega\bigl(\sqrt{\alpha T}\bigr)$ is known to hold for any $\alpha$. Our improved upper bound $\mathcal{O}\bigl(\sqrt{\alpha T(1+\ln(K/\alpha))}\bigr)$ holds for any $\alpha$ and matches the lower bounds for bandits and experts, while interpolating intermediate cases. To prove this result, we use FTRL with $q$-Tsallis entropy for a carefully chosen value of $q \in [1/2, 1)$ that varies with $\alpha$. The analysis of this algorithm requires a new bound on the variance term in the regret. We also show how to extend our techniques to time-varying graphs, without requiring prior knowledge of their independence numbers. Our upper bound is complemented by an improved $\Omega\bigl(\sqrt{\alpha T(\ln K)/(\ln\alpha)}\bigr)$ lower bound for all $\alpha > 1$, whose analysis relies on a novel reduction to multitask learning. This shows that a logarithmic factor is necessary as soon as $\alpha < K$.

One of the primary challenges in online learning environments, is to retain learner engagement. Several different instructional strategies are proposed both in online and offline environments to enhance learner engagement. The Concept Attainment Model is one such instructional strategy that focuses on learners acquiring a deeper understanding of a concept rather than just its dictionary definition. This is done by searching and listing the properties used to distinguish examples from non-examples of various concepts. Our work attempts to apply the Concept Attainment Model to build conceptual riddles, to deploy over online learning environments. The approach involves creating factual triples from learning resources, classifying them based on their uniqueness to a concept into `Topic Markers' and `Common', followed by generating riddles based on the Concept Attainment Model's format and capturing all possible solutions to those riddles. The results obtained from the human evaluation of riddles prove encouraging.

We study multitask online learning in a setting where agents can only exchange information with their neighbors on an arbitrary communication network. We introduce $\texttt{MT-CO}_2\texttt{OL}$, a decentralized algorithm for this setting whose regret depends on the interplay between the task similarities and the network structure. Our analysis shows that the regret of $\texttt{MT-CO}_2\texttt{OL}$ is never worse (up to constants) than the bound obtained when agents do not share information. On the other hand, our bounds significantly improve when neighboring agents operate on similar tasks. In addition, we prove that our algorithm can be made differentially private with a negligible impact on the regret when the losses are linear. Finally, we provide experimental support for our theory.

Complex robot behaviour typically requires the integration of multiple robotic and Artificial Intelligence (AI) techniques and components. Integrating such disparate components into a coherent system, while also ensuring global properties and behaviours, is a significant challenge for cognitive robotics. Using a formal framework to model the interactions between components can be an important step in dealing with this challenge. In this paper we extend an existing formal framework [Clark et al., 2016] to model complex integrated reasoning behaviours of robotic systems; from symbolic planning through to online learning of policies and transition systems. Furthermore the new framework allows for a more flexible modelling of the interactions between different reasoning components.

In this paper, we study the problem of efficient online reinforcement learning in the infinite horizon setting when there is an offline dataset to start with. We assume that the offline dataset is generated by an expert but with unknown level of competence, i.e., it is not perfect and not necessarily using the optimal policy. We show that if the learning agent models the behavioral policy (parameterized by a competence parameter) used by the expert, it can do substantially better in terms of minimizing cumulative regret, than if it doesn't do that. We establish an upper bound on regret of the exact informed PSRL algorithm that scales as $\tilde{O}(\sqrt{T})$. This requires a novel prior-dependent regret analysis of Bayesian online learning algorithms for the infinite horizon setting. We then propose an approximate Informed RLSVI algorithm that we can interpret as performing imitation learning with the offline dataset, and then performing online learning.