arXiv research

We analyze how an observer synchronizes to the internal state of a finite-state information source, using the epsilon-machine causal representation. Here, we treat the case of exact synchronization, when it is possible for the observer to synchronize completely after a finite number of observations. The more difficult …

New approach to understand recurrent policies as FSMs without minimization.

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…

Method infers causal structure from system behaviors using RKHS and kernel $ε$-machines.

New neural stack and Turing Machine architectures prove stability and computational power.

Recurrent neural networks trained on regular languages exhibit stable states that can recover from noise.

Study shows challenges in converting RNNs to FSMs due to computational complexity.

We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct …

Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both…

A new ML algorithm solves complex economic control problems.

Next-gen reservoir computers fail to predict complex processes, highlighting need for better architectures.

Combines machine learning and convex limiting for accurate subgrid flux modeling in shallow-water equations.

New communication standards need to deal with machine-to-machine communications, in which users may start or stop transmitting at any time in an asynchronous manner. Thus, the number of users is an unknown and time-varying parameter that needs to be accurately estimated in order to properly recover the symbols transmit…

Meta-learning algorithms prepare quantum Gibbs states efficiently for NISQ devices.

Machine learning models accurately predict the state and dynamics of reactive mixing.

We implement an all-optical setup demonstrating kernel-based quantum machine learning for two-dimensional classification problems. In this hybrid approach, kernel evaluations are outsourced to projective measurements on suitably designed quantum states encoding the training data, while the model training is processed o…

We use Machine Learning (ML) and system identification validation approaches to estimate neural network models of large-scale Deformable Mirrors (DMs) used in Adaptive Optics (AO) systems. To obtain the training, validation, and test data sets, we simulate a realistic large-scale Finite Element (FE) model of a faceplat…

This work optimizes MCMC algorithms for modern accelerators without synchronization overheads.

The paper explains how continuous language models can produce discrete, interpretable meanings.

Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the t…

Formalizes the Fundamental Theorem of Asset Pricing in Lean 4.

Transformers simulate finite-state automata with fewer layers.

Fewer data weight updates lead to faster convergence in machine learning models.

Enhances reward specification in RL with a novel language-based approach.

A theorem for debiasing machine learning with finite sample guarantees.

This paper develops nudging algorithms using learned surrogates for state estimation in dynamical systems.

Machine learning aids excited-state molecular dynamics studies.

Machine learning promises methods that generalize well from finite labeled data. However, the brittleness of existing neural net approaches is revealed by notable failures, such as the existence of adversarial examples that are misclassified despite being nearly identical to a training example, or the inability of recu…

SMG combines shuffling and momentum for non-convex optimization.

A framework to quantify deployment risk in ML systems, especially for rare states.

Many machine learning, statistical inference, and portfolio optimization problems require minimization of a composition of expected value functions (CEVF). Of particular interest is the finite-sum versions of such compositional optimization problems (FS-CEVF). Compositional stochastic variance reduced gradient (C-SVRG)…

Machine learning speeds up quantum chemical calculations of excited states.

Boosting for label ranking outperforms existing methods.

We introduce a Bayesian approach to discovering patterns in structurally complex processes. The proposed method of Bayesian Structural Inference (BSI) relies on a set of candidate unifilar HMM (uHMM) topologies for inference of process structure from a data series. We employ a recently developed exact enumeration of to…

FaiREE provides fair classification with guarantees for small datasets.

This paper formalizes Uniswap v3 using PTA and FST for rigorous analysis.

Graph Laplacians and machine learning predict properties of finite graphs.

Sharp bounds derived for test error of finite-rank kernel ridge regression.

Study on natural actor-critic for POMDPs with finite memory.

The paper simplifies multi-agent RL dynamics in finite-state Markov games using homogenization.

Excited-state dynamics simulations are a powerful tool to investigate photo-induced reactions of molecules and materials and provide complementary information to experiments. Since the applicability of these simulation techniques is limited by the costs of the underlying electronic structure calculations, we develop an…

Finite presentations for skein algebras linked to gauge field theory.

Gaussian processes are used in machine learning to learn input-output mappings from observed data. Gaussian process regression is based on imposing a Gaussian process prior on the unknown regressor function and statistically conditioning it on the observed data. In system identification, Gaussian processes are used to …

Inverse reinforcement learning (IRL) is the problem of finding a reward function that generates a given optimal policy for a given Markov Decision Process. This paper looks at an algorithmic-independent geometric analysis of the IRL problem with finite states and actions. A L1-regularized Support Vector Machine formula…

Robust topological information commonly comes in the form of a set of persistence diagrams, finite measures that are in nature uneasy to affix to generic machine learning frameworks. We introduce a fast, learnt, unsupervised vectorization method for measures in Euclidean spaces and use it for reflecting underlying chan…

We propose a fast proximal Newton-type algorithm for minimizing regularized finite sums that returns an $ε$-suboptimal point in $\tilde{\mathcal{O}}(d(n + \sqrt{κd})\log(\frac{1}ε))$ FLOPS, where $n$ is number of samples, $d$ is feature dimension, and $κ$ is the condition number. As long as $n > d$, the proposed method…

Neural-Network Quantum States have been recently introduced as an Ansatz for describing the wave function of quantum many-body systems. We show that there are strong connections between Neural-Network Quantum States in the form of Restricted Boltzmann Machines and some classes of Tensor-Network states in arbitrary dime…

This article introduces both a new algorithm for reconstructing epsilon-machines from data, as well as the decisional states. These are defined as the internal states of a system that lead to the same decision, based on a user-provided utility or pay-off function. The utility function encodes some a priori knowledge ex…