The relaxed maximum entropy problem is concerned with finding a probability distribution on a finite set that minimizes the relative entropy to a given prior distribution, while satisfying relaxed max-norm constraints with respect to a third observed multinomial distribution. We study the entire relaxation path for thi…
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “path entropy”
PAN improves graph neural networks using path integrals.
problem Efficiency and performance of graph neural networks.
method PAN uses path integrals to generalize graph Laplacian, incorporating all paths between nodes.
result PAN achieves state-of-the-art performance on benchmark tasks.
EntroPath learns manifold geometry from diffusion paths.
problem Learning geodesic geometry from data graphs with spurious shortcuts.
method Maximum Entropy Path Ensemble Embedding (MERW) with k-step diffusion paths.
result EntroPath converges to squared geodesic distance in the short-time limit.
Path Shadowing Monte-Carloq-fin.MF
A new method predicts future paths using a Monte-Carlo approach.
problem Predicting future financial paths given historical data.
method Path Shadowing Monte-Carlo method using maximum entropy model.
result Yields state-of-the-art predictions for future volatility and option smiles.
Deep nets' complexity and risk are quantified using total path variation.
problem Quantifying the complexity and risk of deep neural networks.
method Using total path variation, the paper establishes relationships between network complexity and statistical risk.
result The statistical risk and metric entropy of deep nets are proportional to the total variation of path weights.
Deep networks avoid bad local minima with no bad valleys.
problem Finding sub-optimal local minima in deep neural networks.
method Analyzing over-parameterized networks with specific activation and loss functions.
result No bad local valleys, implying no sub-optimal strict local minima.
New method generates synthetic time series paths with more flexibility.
problem Restrictions in generating synthetic paths using Brownian reference.
method Introduces Triangular-Reference Schrödinger Bridges (TR-SBTS) for time series generation.
result Generates synthetic paths with more flexibility in stochastic volatility and correlated noise.
PAN uses path integrals for graph convolution and pooling, improving GNN performance.
problem Designing efficient graph convolution and pooling for graph neural networks.
method Path integral based graph convolution and pooling using learnable weights for path lengths.
result PAN achieves state-of-the-art performance on various graph classification/regression tasks.
Entropy regularization improves policy optimization in reinforcement learning.
problem Improving policy optimization in reinforcement learning.
method Entropy regularization is introduced to soften the greedy policy towards a more diverse softmax policy, leading to a continuously parameterized algorithm that interpolates between policy gradient and Q-learning.
result An intermediate algorithm can improve performance in reinforcement learning.
PDNS tackles multimodal sampling challenges using proximal point method.
problem Multimodal distributions with significant barriers between modes.
method Proximal point method on path measures, decomposing into simpler subproblems.
result PDNS effectively promotes thorough exploration across modes.
Conservation laws improve diffusion model training by optimizing likelihood.
problem Training diffusion models with denoising objectives.
method Developed conservation laws based on GEXIT functions for memoryless noise processes.
result Unified characterization of diffusion model likelihood, reducing training to learning marginal posteriors.
The paper calculates the growth rates of billiard languages in hyperbolic polygons.
problem Computing the exponential growth rates of billiard languages in polygons.
method New methods relating to minimal tiling paths.
result Explicit computation of exponential growth rates for even, and bounds for odd.
A Bayesian Perspective of Convolutional Neural Networks through a Deconvolutional Generative Modelcs.CV
Designs a new generative model for images using CNNs and improves generalization and performance.
problem Improving image generation and generalization in CNNs.
method Deconvolutional Generative Model (DGM) using a conjugate prior and Rendering Path Normalization (RPN).
result Improves generalization and performance in semi-supervised and supervised learning tasks.
New method infers population dynamics from snapshots using path space optimization.
problem Recover dynamics of a population from its temporal marginals.
method Grid-free algorithm using Schrödinger bridges coupled via noisy gradient descent in mean-field limit.
result Global convergence to min-entropy estimator with end-to-end theoretical guarantees.
We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero probability for only a small number of actions. This addresses the main drawback of the …
Unified approach to path planning using probabilistic inference on factor graphs.
problem Path planning problems using probabilistic inference.
method Unified framework using probabilistic factor graphs and message composition rules.
result Unified approach includes various algorithms like Sum-product, Max-product, Dynamic programming, and mixed criteria.
Introducing user-prescribed constraints in Markov chains for nonlinear dimensionality reductioncs.LG
New method adds user constraints to Markov chains for better data reduction.
problem No systematic framework to impose user-defined constraints on Markov chains.
method Path entropy maximization to derive transition probabilities with user constraints.
result Improved nonlinear dimensionality reduction with user-prescribed constraints.
New algorithm computes Schrödinger Bridge for unpaired data translation.
problem Computing optimal transport maps for unpaired data translation.
method Schrödinger Bridge Flow, a discretization of a flow of path measures.
result Eliminates the need to train multiple DDM-like models.
We develop a technique based on Malliavin-Bismut calculus ideas, for asymptotic expansion of dual control problems arising in connection with exponential indifference valuation of claims, and with minimisation of relative entropy, in incomplete markets. The problems involve optimisation of a functional of Brownian path…
A new algorithm learns MAGs from data more efficiently using entropy.
problem Learning MAGs from data is unstable and computationally expensive.
method Uses entropy estimation and refined Markov property to score MAGs.
result Algorithm is polynomial in number of nodes and outperforms existing methods.
Optimizes exploration in networks by interpolating between random and deterministic paths.
problem Balancing exploitation and exploration in network routing with constraints.
method Developed a constrained randomized shortest-paths framework using Lagrangian duality and iterative procedures.
result Optimal routing policy that interpolates between random and deterministic paths while satisfying constraints.
Analyzes how BPE tokenisation affects corpus statistics and model entropy in transformer models.
problem Understanding how natural language properties relate to tokenisation schemes in transformer models.
method Analyzes Shannon entropy of corpora under Zipfian distribution, investigates BPE transformations, trains language models, and uses attention diagnostics.
result Transformer models trained on BPE-tokenised corpora increasingly agree with Zipfian predictions as BPE depth increases, indicating reduced local token dependencies.
Researchers create a teapot model for Mandelbrot set, proving connectedness.
problem Understanding the connectedness of the outside part of the Mandelbrot set.
method Defined a 'Master teapot' model and generalized kneading theory for principal veins.
result Outside part of the 'Thurston set' is path connected.
Geometrically constructs twist-field correlation functions in CFT.
problem Understanding entanglement entropy in quantum systems.
method Using Cauchy-Hadamard renormalization of Polyakov anomaly integral on surfaces with conical singularities.
result Provides a purely mathematical interpretation of entanglement entropy results.
REGS samples from unnormalized distributions using gradient flow and neural networks.
problem Sampling from unnormalized distributions with high accuracy and efficiency.
method REGS is a particle method that iteratively transforms samples from a reference distribution to match an unnormalized target distribution using Wasserstein gradient flow and neural networks.
result REGS outperforms state-of-the-art methods in sampling from challenging multimodal distributions and real datasets.
Unified approach to structured prediction combining entropy regularization and neuro-symbolic logic.
problem Structured prediction challenges due to large output spaces and insufficient labeled data.
method Neuro-symbolic entropy regularization loss that restricts entropy regularization to valid structures.
result Models predict more accurately and are more likely to be valid.
This paper studies neural networks with bounded norms to avoid the curse of dimensionality.
problem The curse of dimensionality in approximating functions by neural networks.
method Investigates over-parameterized two-layer neural networks with norm constraints in RKHS.
result Improved sample complexity and generalization bounds for neural networks with bounded norms.
Develops variable-lag Granger causality and Transfer Entropy for time series analysis.
problem Fixed time delay assumption in Granger causality and Transfer Entropy does not hold in many applications.
method Variable-lag Granger causality and Transfer Entropy, using optimal warping path of Dynamic Time Warping (DTW).
result Proposed methods perform better than existing methods in both simulated and real-world datasets.
Optimizes diffusion processes for target distributions.
problem Efficiently generating target distributions from point masses.
method Stochastic interpolant framework with conditional expectation drift.
result Optimal diffusion coefficient minimizes path-space KL divergence.
Estimating the entropy based on data is one of the prototypical problems in distribution property testing and estimation. For estimating the Shannon entropy of a distribution on elements with independent samples, [Paninski2004] showed that the sample complexity is sublinear in , and [Valiant--Valiant2011] showed…
Generative flow networks use RL to learn probabilistic models efficiently.
problem Training generative models with RL for compositional discrete objects.
method Reformulate GFlowNet training as entropy-regularized RL with specific reward and regularizer.
result Entropy-regularized RL can be competitive with established GFlowNet training methods.
New method reduces regret for sparse adversarial SSP problems.
problem Sparse adversarial Stochastic Shortest Path problem.
method Proposed -norm regularizers for adaptive sparsity.
result Regret scales with instead of .
A new method for stochastic optimal control improves accuracy over existing techniques.
problem Improving the accuracy of stochastic optimal control for noisy systems.
method Stochastic Optimal Control Matching (SOCM) using Iterative Diffusion Optimization (IDO) with path-wise reparameterization trick.
result SOCM achieves lower error than existing techniques for three out of four control problems, sometimes by an order of magnitude.
A new method uses string method to explore diffusion models.
problem Understanding the geometry of learned distributions in diffusion models.
method String method to compute continuous paths between samples.
result The string method identifies realistic morphing sequences and transition pathways.
New algorithm selects relevant variables in high-dimensional graphical models.
problem Automatic selection of relevant variables in high-dimensional graphical models.
method Extends Chow and Liu's algorithm using mutual information and entropy coefficient of determination.
result Outperforms existing methods in selecting variables with explanatory power.
The paper develops fair machine learning models using causal path-specific effects.
problem Fairness in machine learning models under causal constraints.
method Lagrange multiplier approach for infinite-dimensional functional estimation, closed-form solutions for constrained optimization.
result Theoretical and flexible semiparametric estimation strategies for fair predictions.
A discrete diffusion model learns denoising, scoring, and bridging in different coordinates.
problem Understanding what a discrete diffusion model learns in different coordinate systems.
method Rigorous derivation of continuous-time Markov chain ELBO, Oracle Distance theorem, and exact coordinates for optimizer.
result The negative ELBO is exactly equal to the data entropy plus the path KL from the oracle reverse process to the learned one.
Learning Stochastic Thermodynamics Directly from Correlation and Trajectory-Fluctuation Currentscond-mat.stat-mech
New method learns stochastic thermodynamics from system currents.
problem Understanding entropy production in complex dynamical systems.
method Constructs learning framework using currents and machine learning loss functions.
result Derives loss functions for thermodynamic functions directly from dynamics.
Gradient descent implicitly follows regularization for general losses.
problem The implicit bias of gradient descent methods in machine learning.
method Empirical risk minimization over linear predictors with arbitrary convex, strictly decreasing losses.
result Gradient descent and regularization paths converge to the same direction for non-attained risks.
Extends RSP model with net flow and capacity constraints for better network analysis.
problem Improving shortest path models with net flows and capacity constraints.
method Developed net flow RSP model and introduced capacity constraints. Proposed algorithms for computing expected routing costs and solving constrained problems using Lagrangian duality.
result Net flow RSP dissimilarity measure is competitive with state-of-the-art dissimilarities.
A path integral on a link complement of a three-sphere fixes a vector (the "link state") in Chern-Simons theory. The link state can be written in a certain basis with the colored link invariants as its coefficients. We use symmetric webs to systematically compute the colored link invariants, by which we can write down …
The paper shows how policy regularization acts like an adversary to improve robustness.
problem Improving robustness of learned policies in reinforcement learning.
method Using convex duality, the paper characterizes adversarial reward perturbations and provides generalization guarantees.
result Policy regularization acts as an adversary to improve robustness against worst-case reward perturbations.
New method for Ricci flows on graphs that can handle changing structures.
problem Challenges of Ricci flows on graphs with evolving structures.
method Introducing super Ricci flows and studying heat flow on singular graphs.
result Consistency with classical Ricci flows in a discrete to continuum limit.
A neural network derived from first principles using MaxEnt.
problem Developing a neural network from first principles.
method Derived a neural network using the principle of Maximum Entropy, with linear dimension-reducing transformations and conditional mean estimators.
result Unified theoretical justification for activation functions like sigmoid, softplus, and relu.
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that softmax consistent action values correspond to optimal entropy regularized policy pro…
In this work we present an analytical model, based on the path-integral formalism of Statistical Mechanics, for pricing options using first-passage time problems involving both fixed and deterministically moving absorbing barriers under possible non-gaussian distributions of the underlying object. We adapt to our probl…
RG-2 flow preserves area monotonicity in asymptotically flat spacetimes.
problem Mathematical and physical properties of RG-2 flow compared to Ricci flow.
method Study of RG-2 flow in asymptotically flat spacetimes with time-symmetric foliation.
result Area of a closed surface is monotonous under RG-2 flow, similar to Ricci flow.
EGMU optimizes portfolios using KL divergence, ensuring positive solutions.
problem Constructing multi-factor target-exposure portfolios efficiently and accurately.
method Convex optimization framework minimizing KL divergence, with explicit solvers.
result Established feasibility and uniqueness of strictly positive solutions under convex-hull conditions.