A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Enhances early-exit neural networks for anytime classification.
The study introduces anytime learning schedules for large language models without fixed horizons.
We introduce a novel incremental decision tree learning algorithm, Hoeffding Anytime Tree, that is statistically more efficient than the current state-of-the-art, Hoeffding Tree. We demonstrate that an implementation of Hoeffding Anytime Tree---"Extremely Fast Decision Tree", a minor modification to the MOA implementat…
Anytime MiniBatch speeds up online distributed optimization by handling slow nodes.
The pioneer deep neural networks (DNNs) have emerged to be deeper or wider for improving their accuracy in various applications of artificial intelligence. However, DNNs are often too heavy to deploy in practice, and it is often required to control their architectures dynamically given computing resource budget, i.e., …
This work accelerates gradient descent with anytime convergence guarantees.
Optimizes SGD for anytime neural networks, improving accuracy.
Transforms any test into anytime-valid with sample savings.
Monte Carlo algorithms simulate some prescribed number of samples, taking some random real time to complete the computations necessary. This work considers the converse: to impose a real-time budget on the computation, which results in the number of samples simulated being random. To complicate matters, the real time t…
This paper presents a new anytime algorithm for the marginal MAP problem in graphical models. The algorithm is described in detail, its complexity and convergence rate are studied, and relations to previous theoretical results for the problem are discussed. It is shown that the algorithm runs in polynomial-time if the …
We propose a new anytime hierarchical clustering method that iteratively transforms an arbitrary initial hierarchy on the configuration of measurements along a sequence of trees we prove for a fixed data set must terminate in a chain of nested partitions that satisfies a natural homogeneity requirement. Each recursive …
We introduce a new sequential Monte Carlo algorithm we call the particle cascade. The particle cascade is an asynchronous, anytime alternative to traditional particle filtering algorithms. It uses no barrier synchronizations which leads to improved particle throughput and memory efficiency. It is an anytime algorithm i…
APGAI identifies good arms anytime with fixed budget.
Develops anytime-valid stopping rules for SGD based on observed trajectory.
New algorithm guarantees performance on noisy data.
Optimizes random forest inference by defining step order to maximize accuracy.
GAAVI offers anytime-valid tests for CMF global null and contrasts.
We consider the classical problem of prediction with expert advice. In the fixed-time setting, where the time horizon is known in advance, algorithms that achieve the optimal regret are known when there are two, three, or four experts or when the number of experts is large. Much less is known about the problem in the a…
This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regret of the policy is of order log(n). They have also shown that such a …
CSA fills a gap in RLVR-trained LLM deployment by providing anytime-valid selective risk control.
I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in hindsight) and comes with the strongest finite-time regret guarantees for a hori…
Paper develops a new watermarking framework for LLMs.
Paper offers anytime-valid inference for causal parameters using DML.
Adaptive auditing improves AI robustness testing with anytime-valid guarantees.
Deployment of deep neural networks (DNNs) in safety- or security-critical systems requires provable guarantees on their correct behaviour. A common requirement is robustness to adversarial perturbations in a neighbourhood around an input. In this paper we focus on the norm and aim to compute, for a trained DNN an…
Belief Propagation has been widely used for marginal inference, however it is slow on problems with large-domain variables and high-order factors. Previous work provides useful approximations to facilitate inference on such models, but lacks important anytime properties such as: 1) providing accurate and consistent mar…
Transfer learning techniques have been widely used in the reality that it is difficult to obtain sufficient labeled data in the target domain, but a large amount of auxiliary data can be obtained in the relevant source domain. But most of the existing methods are based on offline data. In practical applications, it is …
Develops an anytime-valid framework for optimal policy identification from logged contextual bandit data.
An online reinforcement learning algorithm is anytime if it does not need to know in advance the horizon T of the experiment. A well-known technique to obtain an anytime algorithm from any non-anytime algorithm is the "Doubling Trick". In the context of adversarial or stochastic multi-armed bandits, the performance of …
New algorithm identifies best arm with optimal budget usage.
Four geometries govern sequential and distribution-free inference.
CITE algorithm provides anytime-valid certification of model outputs.
Anytime-valid confirmation of label-shift corrections
Improves decision tree performance by correcting split selection errors.
Paper improves PAC-Bayes bounds for various loss types.
Extends FC-RAG to anytime-valid sequential coverage for language model swarms.
HATT improves online decision tree ensembles by using a more eager splitting strategy.
Unified framework for ensemble sampling in nonlinear contextual bandits with provable regret bounds.
PITMonitor monitors model calibration over time with formal error guarantees.
Paper tackles safe combinatorial semi-bandits with risk constraints.
E-C2ST uses E-values for high-dimensional data two-sample tests.
We describe an embarrassingly parallel, anytime Monte Carlo method for likelihood-free models. The algorithm starts with the view that the stochasticity of the pseudo-samples generated by the simulator can be controlled externally by a vector of random numbers u, in such a way that the outcome, knowing u, is determinis…
Bounded rationality investigates utility-optimizing decision-makers with limited information-processing power. In particular, information theoretic bounded rationality models formalize resource constraints abstractly in terms of relative Shannon information, namely the Kullback-Leibler Divergence between the agents' pr…
In this paper, we study the behavior of the Hedge algorithm in the online stochastic setting. We prove that anytime Hedge with decreasing learning rate, which is one of the simplest algorithm for the problem of prediction with expert advice, is surprisingly both worst-case optimal and adaptive to the easier stochastic …
Extends risk control to adaptive data collection, anytime-valid guarantees.
This paper presents a multi-staged approach to nonmyopic adaptive Gaussian process optimization (GPO) for Bayesian optimization (BO) of unknown, highly complex objective functions that, in contrast to existing nonmyopic adaptive BO algorithms, exploits the notion of macro-actions for scaling up to a further lookahead t…
Study on computable online learning with new conditions and complexities.
We propose an adaptive sampling approach for multiple testing which aims to maximize statistical power while ensuring anytime false discovery control. We consider distributions whose means are partitioned by whether they are below or equal to a baseline (nulls), versus above the baseline (actual positives). In addi…