arXiv research

IDS algorithm optimizes sequential decisions in various monitoring settings.

New Thompson sampling algorithm for stochastic partial monitoring achieves logarithmic regret.

IDS optimizes regret in stochastic partial monitoring with linear rewards.

New minimax theorem connects Bayesian and minimax regret in partial monitoring.

Algorithm reduces regret in complex game scenarios.

Partial monitoring is a generalization of the well-known multi-armed bandit framework where the loss is not directly observed by the learner. We complete the classification of finite adversarial partial monitoring to include all games, solving an open problem posed by Bartok et al. [2014]. Along the way we simplify and…

Partial-monitoring games constitute a mathematical framework for sequential decision making problems with imperfect feedback: The learner repeatedly chooses an action, opponent responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which are fixed functions of the action a…

New algorithms reduce regret in both stochastic and adversarial partial monitoring problems.

Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner suffers a loss and receives a feedback signal. The goal of the learner is to mi…

In approachability with full monitoring there are two types of conditions that are known to be equivalent for convex sets: a primal and a dual condition. The primal one is of the form: a set C is approachable if and only all containing half-spaces are approachable in the one-shot game; while the dual one is of the form…

Calibrated strategies can be obtained by performing strategies that have no internal regret in some auxiliary game. Such strategies can be constructed explicitly with the use of Blackwell's approachability theorem, in an other auxiliary game. We establish the converse: a strategy that approaches a convex $B$-set can be…

New algorithm minimizes expert selection regret in partial bandit feedback.

We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and "hard" problems. For easy problems, it additionally achieves logarithmic individual…

The method and characteristics of several approaches to the pricing of discretely monitored arithmetic Asian options on stocks with discrete, absolute dividends are described. The contrast between method behaviors for options with an Asian tail and those with monitoring throughout their lifespan is emphasized. Rates of…

Algorithm selects best sensor tests for unknown outcomes.

Study optimizes inspection and monitoring of deteriorating structures using POMDPs.

Improved ExO method achieves near-optimal bounds in both stochastic and adversarial settings.

A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partiall…

The paper proposes a method to monitor deep learning predictions for retraining, reducing costs.

Neural networks compress and sample WDN contamination dynamics efficiently.

New deep probabilistic model handles missing data in time series forecasting.

Study on multi-agent decision making complexity, showing sample efficiency gaps.

This paper presents a new asymptotic expansion method for pricing continuously monitoring barrier options. In particular, we develops a semi-group expansion scheme for the Cauchy-Dirichlet problem in the second-order parabolic partial differential equations (PDEs) arising in barrier option pricing. As an application, w…

Expert-guided model improves seismic compliance monitoring.

Across numerous applications, forecasting relies on numerical solvers for partial differential equations (PDEs). Although the use of deep-learning techniques has been proposed, actual applications have been restricted by the fact the training data are obtained using traditional PDE solvers. Thereby, the uses of deep-le…

A new method uses active learning to monitor industrial processes more accurately.

Optimal online learning algorithms for label-efficient prediction and bandits.

We prove the statistical consistency of kernel Partial Least Squares Regression applied to a bounded regression learning problem on a reproducing kernel Hilbert space. Partial Least Squares stands out of well-known classical approaches as e.g. Ridge Regression or Principal Components Regression, as it is not defined as…

Most of the empirical studies on stochastic volatility dynamics favor the 3/2 specification over the square-root (CIR) process in the Heston model. In the context of option pricing, the 3/2 stochastic volatility model is reported to be able to capture the volatility skew evolution better than the Heston model. In this …

AI systems that explain their decisions can be monitored for harmful intentions.

Spreading processes are often modelled as a stochastic dynamics occurring on top of a given network with edge weights corresponding to the transmission probabilities. Knowledge of veracious transmission probabilities is essential for prediction, optimization, and control of diffusion dynamics. Unfortunately, in most ca…

Neural Jump ODEs improve online filtering and classification with robust performance.

Simple online monitor detects unsafe LLM outputs.

Deep CNNs struggle with rare taxa; one-class classifiers help identify them.

This research tackles monitoring machine learning algorithms post-deployment, addressing performativity issues.

Paper characterizes minimax regret rates for online ranking with top-k feedback.

Paper improves ETF tail-risk monitoring reliability.

Adaptive activity monitoring framework for wearable sensors.

PITMonitor monitors model calibration over time with formal error guarantees.

The paper adds explanation to predictive process monitoring.

A new method monitors unstructured 3D shapes without registration.

Focuses on monitoring and explaining models in real-world applications.

Surveying low-cost sensors for air quality monitoring and calibration.

Neural system optimizes glucose levels in diabetics.

We present a numerical scheme to calculate fluctuation identities for exponential Lévy processes in the continuous monitoring case. This includes the Spitzer identities for touching a single upper or lower barrier, and the more difficult case of the two-barriers exit problem. These identities are given in the Fourier-L…

Optimal probing framework for scalable network monitoring.

The paper proposes a method to create efficient remote monitoring models.

DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.