arXiv research

New algorithm minimizes regret in stochastic linear bandits with perturbed history.

We propose an online algorithm for cumulative regret minimization in a stochastic multi-armed bandit. The algorithm adds $O(t)$ i.i.d. pseudo-rewards to its history in round $t$ and then pulls the arm with the highest average reward in its perturbed history. Therefore, we call it perturbed-history exploration (PHE). Th…

EVILL uses randomised perturbations to improve exploration in bandit problems.

Novel PCA method for high-dimensional inverse problems.

The restricted planar three-body problem has a rich history, yet many unanswered questions still remain. In the present paper we prove the existence of a global surface of section near the smaller body in a new range of energies and mass ratios for which the Hill's region still has three connected components. The appro…

Brief history and challenges of interpretable machine learning.

Exact simulation method for market impact estimation under various execution strategies.

Two randomized algorithms improve regret bounds for generalized linear bandits.

This paper treats prediction markets as Bayesian inverse problems to quantify uncertainty and identify event outcomes.

FRESH combines patient-level and aggregate-level data for better clinical decision making.

Bayesian inference over admissible histories leads to irreversible kinetics.

HS-FNO models non-Markovian PDEs by learning history and future states.

Overview of affine surface area and its history.

Survey of Baum-Connes conjecture history and methods.

A technique identifies memoryless algorithms approximating memory-dependent optimization methods.

Survey on DDVV-type inequalities, their history, and recent developments.

New method learns representations for decision forests using input perturbation.

SRMC framework reduces Monte Carlo variance by history-based sampling in high-dimensional spaces.

Paper analyzes history-based RL methods for MDPs, introduces a theoretical framework and practical algorithm.

Using the mechanics of creep in material sciences as a metaphor, we present a general framework to understand the evolution of financial, economic and social systems and to construct scenarios for the future. In a nutshell, highly non-linear out-of-equilibrium systems subjected to exogenous perturbations tend to exhibi…

Paper robustifies reinforcement learning agents against action space perturbations.

Neural networks improve cancer risk prediction from family history data.

The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.

It is shown how the generating functional method of De Dominicis can be used to solve the dynamics of the original version of the minority game (MG), in which agents observe real as opposed to fake market histories. Here one again finds exact closed equations for correlation and response functions, but now these are de…

Two major financial market complexities are transaction costs and uncertain volatility, and we analyze their joint impact on the problem of portfolio optimization. When volatility is constant, the transaction costs optimal investment problem has a long history, especially in the use of asymptotic approximations when th…

This paper suggests claim history will be deprecated in future auto insurance rates.

We present in this chapter (Chapter II) the history of ideas which lead up to the development of modern knot theory. We are more detailed when pre-XX century history is reported. With more recent times we are more selective, stressing developments related to Jones type invariants of links. In the Appendix, A.Przybyszew…

Paper tackles reinforcement learning for STL specifications with state history.

We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirec…

We give an explicit definition of decentralization and show you that decentralization is almost impossible for the current stage and Bitcoin is the first truly noncentralized currency in the currency history. We propose a new framework of noncentralized cryptocurrency system with an assumption of the existence of a wea…

Cold-start PV forecasting uses synthetic histories to train time-series foundation models.

A major hurdle to clinical translation of brain-machine interfaces (BMIs) is that current decoders, which are trained from a small quantity of recent data, become ineffective when neural recording conditions subsequently change. We tested whether a decoder could be made more robust to future neural variability by train…

Epsilon-machines are minimal, unifilar presentations of stationary stochastic processes. They were originally defined in the history machine sense, as hidden Markov models whose states are the equivalence classes of infinite pasts with the same probability distribution over futures. In analyzing synchronization, though…

Robust RL with learned optimal adversary improves agent performance under adversarial state observations.

Combining deep learning and ensemble smoothers for better history matching.

New framework handles dynamic contexts in reinforcement learning.

A dangerously brief history of the developments of the main ideas in economics, as observed by a physicist, is given. This was published in 'Econophysics of Stock and Other Markets', Eds. A. Chatterjee, B. K. Chakrabarti, New Economic Windows Series, Springer, Milan, 2006, pp~219-224.

Transformers improve Alzheimer's disease progression prediction by accounting for irregular biomarker histories.

Foundation models improve wage gap decomposition by capturing omitted career history factors.

Marden's Tameness Conjecture predicts that every hyperbolic 3-manifold with finitely generated fundamental group is homeomorphic to the interior of a compact 3-manifold. It was recently established by Agol and Calegari-Gabai. We will survey the history of work on this conjecture and discuss its many applications.

Network growth processes can be understood as generative models of the structure and history of complex networks. This point of view naturally leads to the problem of network archaeology: reconstructing all the past states of a network from its structure---a difficult permutation inference problem. In this paper, we in…

Deep learning calibrates CO2 storage formations from seismic and well data.

A new method uses a frozen language model to improve sample efficiency in reinforcement learning.

HDT improves MCMC on graphs with history-dependent sampling.

New scheme adapts batch size for faster variance-reduced algorithms.

Paper presents a method for recognizing human actions using GLAC features from motion and static images.

Rhino learns causal relationships from time series data with history-dependent noise.

Proposes using frequent sequences to improve sequential recommendation models.