arXiv research

Single model detects abnormal samples across diverse tasks.

EntroPath learns manifold geometry from diffusion paths.

New analysis of annealing paths in sampling and estimation.

This article provides the first procedure for computing a fully data-dependent interval that traps the mixing time $t_{\text{mix}}$ of a finite reversible ergodic Markov chain at a prescribed confidence level. The interval is computed from a single finite-length sample path from the Markov chain, and does not require t…

Estimates mixing coefficients of geometrically ergodic Markov processes from a single sample path.

This paper optimizes paths for generative models using kinetic energy.

Have you ever wondered how your feature space is impacting the prediction of a specific sample in your dataset? In this paper, we introduce Single Sample Feature Importance (SSFI), which is an interpretable feature importance algorithm that allows for the identification of the most important features that contribute to…

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of hardware-efficient ConvNets by automating this process. However, the NAS problem remains challen…

A new method reduces Monte Carlo variance for financial payoffs.

We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the system is available. We consider the Nearest Neighbor Q-Learning (NNQL) algorithm to…

We develop generic and efficient importance sampling estimators for Monte Carlo evaluation of prices of single- and multi-asset European and path-dependent options in asset price models driven by Lévy processes, extending earlier works which focused on the Black-Scholes and continuous stochastic volatility models. Usin…

C-Learning estimates reachability over time to solve multi-goal tasks.

The literature on statistical learning for time series assumes the asymptotic independence or ``mixing' of the data-generating process. These mixing assumptions are never tested, nor are there methods for estimating mixing rates from data. We give an estimator for the $β$-mixing rate based on a single stationary sample…

Can we reduce the search cost of Neural Architecture Search (NAS) from days down to only few hours? NAS methods automate the design of Convolutional Networks (ConvNets) under hardware constraints and they have emerged as key components of AutoML frameworks. However, the NAS problem remains challenging due to the combin…

Policy mirror ascent achieves Nash equilibrium in mean field games without a population generative model.

StrokeCoder uses Transformers to generate images from single examples.

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the latency constraint of a mobile device? Neural Architecture Search (NAS) for ConvNet design is a challenging problem due to the combinatorially large design space and search time (at least 200 GPU-hours…

One-shot path planning for multiple agents using neural networks.

Paper presents a copula-based method to efficiently generate correlated sample paths from multi-step time series models.

This paper is concerned with a recently developed paradigm for population-based optimization, termed particle filter optimization (PFO). This paradigm is attractive in terms of coherence in theory and easiness in mathematical analysis and interpretation. Current PFO algorithms only work for single-objective optimizatio…

Deep RL optimizes processing paths to desired material structures.

New method for predicting paths of unpredictable objects with high confidence.

A conformal procedure improves CoT reasoning by aggregating reasoning paths and calibrating abstention rules.

Blending multiple convolutional kernels is proved advantageous in neural architecture design. However, current two-stage neural architecture search methods are mainly limited to single-path search spaces. How to efficiently search models of multi-path structures remains a difficult problem. In this paper, we are motiva…

In this paper we outline methodology to efficiently simulate (jump) diffusion bridge sample paths without discretisation error. We achieve this by considering the simulation of conditioned (jump) diffusion bridge sample paths in light of recent work developing a mathematical framework for simulating finite dimensional …

Paper proposes method for generating paths of stochastic volatility CGMY process for option pricing.

We provide theoretical analysis of the statistical and computational properties of penalized $M$-estimators that can be formulated as the solution to a possibly nonconvex optimization problem. Many important estimators fall in this category, including least squares regression with nonconvex regularization, generalized …

Study non-parametric value function estimation from a single path.

This work reduces DIM computation costs by training neural networks on single MC paths.

For a variety of regularized optimization problems in machine learning, algorithms computing the entire solution path have been developed recently. Most of these methods are quadratic programs that are parameterized by a single parameter, as for example the Support Vector Machine (SVM). Solution path algorithms do not …

The paper proposes a method to infer differentiation trees from RNA velocity data.

GH-PID uses guided harmonic paths for efficient SOT with interpretable diagnostics.

New algorithms sample from complex path measures using neural networks.

We propose a new proximal, path-following framework for a class of constrained convex problems. We consider settings where the nonlinear---and possibly non-smooth---objective part is endowed with a proximity operator, and the constraint set is equipped with a self-concordant barrier. Our approach relies on the followin…

The spectral gap $γ$ of a finite, ergodic, and reversible Markov chain is an important parameter measuring the asymptotic rate of convergence. In applications, the transition matrix $P$ may be unknown, yet one sample of the chain up to a fixed time $n$ may be observed. We consider here the problem of estimating $γ$ fro…

The paper defines conditions for Gaussian process sample path regularity.

Large deviations for fat tailed distributions, i.e. those that decay slower than exponential, are not only relatively likely, but they also occur in a rather peculiar way where a finite fraction of the whole sample deviation is concentrated on a single variable. The regime of large deviations is separated from the regi…

Flow Matching enables robust training of CNFs with various probability paths.

VFMs use noise adapters to conditionally generate images in one step.

Itô maps provide a method for any-step SDE integration.

GANs generate samples from time series data.

End-to-end KBQA system learns from multiple reasoning paths without labeled paths.

A large GPS dataset reveals that a single route often covers 60% of travel observations.

New methods improve Monte Carlo estimation of partition functions.

New findings show score matching's accuracy doesn't ensure numerical stability in diffusion sampling.

SPO optimizes LLMs by eliminating group-based baselines and variance issues.

Model rough volatility using RDEs with correlated Brownian motion and fractional Brownian motion.

New algorithm reduces MFGs with common noise complexity.