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.
HS-FNO models non-Markovian PDEs by learning history and future states.
Paper tackles reinforcement learning for STL specifications with state history.
SRMC framework reduces Monte Carlo variance by history-based sampling in high-dimensional spaces.
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…
Paper analyzes history-based RL methods for MDPs, introduces a theoretical framework and practical algorithm.
Recurrent networks learn beliefs from history in partially observable environments.
HDT improves MCMC on graphs with history-dependent sampling.
We propose an online algorithm for cumulative regret minimization in a stochastic multi-armed bandit. The algorithm adds i.i.d. pseudo-rewards to its history in round and then pulls the arm with the highest average reward in its perturbed history. Therefore, we call it perturbed-history exploration (PHE). Th…
Neural networks improve cancer risk prediction from family history data.
Brief history and challenges of interpretable machine learning.
Users form information trails as they browse the web, checkin with a geolocation, rate items, or consume media. A common problem is to predict what a user might do next for the purposes of guidance, recommendation, or prefetching. First-order and higher-order Markov chains have been widely used methods to study such se…
Neurons in cortical circuits exhibit coordinated spiking activity, and can produce correlated synchronous spikes during behavior and cognition. We recently developed a method for estimating the dynamics of correlated ensemble activity by combining a model of simultaneous neuronal interactions (e.g., a spin-glass model)…
Intelligent agents can cope with sensory-rich environments by learning task-agnostic state abstractions. In this paper, we propose an algorithm to approximate causal states, which are the coarsest partition of the joint history of actions and observations in partially-observable Markov decision processes (POMDP). Our m…
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…
We introduce LAMP: the Linear Additive Markov Process. Transitions in LAMP may be influenced by states visited in the distant history of the process, but unlike higher-order Markov processes, LAMP retains an efficient parametrization. LAMP also allows the specific dependence on history to be learned efficiently from da…
Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief sta…
A new method uses a frozen language model to improve sample efficiency in reinforcement learning.
Dynamical-VAE learns causal dynamics from POMDPs using future information.
Proposes using frequent sequences to improve sequential recommendation models.
Develops a new model for RLHF accounting for partially observed states and intermediate feedback.
ETC learns minimal representations for reinforcement learning in POMDPs.
Bayesian inference over admissible histories leads to irreversible kinetics.
Study on future-dependent value functions for off-policy evaluation in complex environments.
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach, teacher forcing, guides a model with reference output history during training. Th…
Overview of affine surface area and its history.
Survey on DDVV-type inequalities, their history, and recent developments.
We solve POMDPs by approximating them as finite-state MDPs.
The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.
Deep neural networks with memory learn reduced equations from partial data.
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…
This paper suggests claim history will be deprecated in future auto insurance rates.
This work tackles large action spaces in RL by binarizing actions.
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…
A framework for analyzing financial systems under scenario constraints.
A Longitudinal Attribute-Conditioned Neural Network (LANTERN) framework for modeling health-state transition probabilities in irregular longitudinal data.
New framework uses cohomology to analyze probabilistic distortions and arbitrage.
BLOB combines organic and bandit signals for better user interest estimation.
This paper gives a survey of recent progress in isoparametric functions and isoparametric hypersurfaces, mainly in two directions. (1) Isoparametric functions on Riemannian manifolds, including exotic spheres. The existences and non-existences will be considered. (2) The Yau conjecture on the first eigenvalues of the e…
A new method predicts future paths using a Monte-Carlo approach.
SnAp approximates RTRL for online training of sparse recurrent networks.
We propose Generative Predecessor Models for Imitation Learning (GPRIL), a novel imitation learning algorithm that matches the state-action distribution to the distribution observed in expert demonstrations, using generative models to reason probabilistically about alternative histories of demonstrated states. We show …
We propose a new online algorithm for cumulative regret minimization in a stochastic linear bandit. The algorithm pulls the arm with the highest estimated reward in a linear model trained on its perturbed history. Therefore, we call it perturbed-history exploration in a linear bandit (LinPHE). The perturbed history is …
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…
These are lecture notes prepared for the summer school "Geometric, algebraic and topological methods in quantum field theory", held in Villa de Leyva in July 2017. Our goal is to provide an introduction to a conjecture of Chern that states that the Euler characteristic of a closed affine manifold vanishes. We present p…
Cold-start PV forecasting uses synthetic histories to train time-series foundation models.
This research note combines two methods that have recently improved the state of the art in language modeling: Transformers and dynamic evaluation. Transformers use stacked layers of self-attention that allow them to capture long range dependencies in sequential data. Dynamic evaluation fits models to the recent sequen…
We study the restless bandit associated with an extremely simple scalar Kalman filter model in discrete time. Under certain assumptions, we prove that the problem is indexable in the sense that the Whittle index is a non-decreasing function of the relevant belief state. In spite of the long history of this problem, thi…
Combining deep learning and ensemble smoothers for better history matching.