Research
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.

169,291 papers · 148 categories

Trend · papers per month

14274154 · Feb 202019922001200920182026
48 results for Parallel tempering

New adaptive temperature selection improves parallel tempering efficiency.

problem Enhancing mixing in multi-modal distributions using parallel tempering.
method Adaptive temperature selection using policy gradient approach.
result Lower integrated autocorrelation times achieved compared to traditional methods.

Improves Bayesian neural learning efficiency with surrogate-assisted parallel tempering.

problem Challenges in Bayesian neural learning due to large models and data.
method Combines parallel tempering MCMC with surrogate-assisted optimization for computationally expensive models.
result Significantly lowers computational cost while maintaining quality in decision making.

In this short note, we show how the parallel adaptive Wang-Landau (PAWL) algorithm of Bornn et al. (2013) can be used to automate and improve simulated tempering algorithms. While Wang-Landau and other stochastic approximation methods have frequently been applied within the simulated tempering framework, this note demo…

2013-05-22abs ↗pdf ↗

Enhances gradient-based discrete samplers with parallel tempering for multimodal distributions.

problem Local minima in high-dimensional, multimodal discrete distributions.
method Combines parallel tempering with discrete Langevin proposal, using Metropolis criterion for swaps.
result Significantly faster mixing and better sampling from complex distributions.

In this paper we demonstrate that tempering Markov chain Monte Carlo samplers for Bayesian models by recursively subsampling observations without replacement can improve the performance of baseline samplers in terms of effective sample size per computation. We present two tempering by subsampling algorithms, subsampled…

2014-01-28abs ↗pdf ↗

A new method uses surrogate models to speed up landscape evolution model inference.

problem Complex and computationally expensive landscape evolution models.
method Surrogate-assisted parallel tempering for Bayesian inversion.
result Significant reduction in computational cost with preserved solution quality.

An infinite parallel tempering bouncy particle sampler improves sampling efficiency for multimodal distributions.

problem Sampling from complex posterior distributions with high accuracy and efficiency.
method Introduced an infinite parallel tempering bouncy particle sampler (BPS-PT) to accelerate convergence.
result Demonstrated improved sampling efficiency for multimodal distributions through numerical simulations.

New sampler tackles noisy posterior sampling with multiple modes.

problem Efficient sampling from complex posterior distributions with multiple isolated modes.
method Integrates parallel tempering with Nosé-Hoover dynamics for stochastic gradient.
result Efficiently draws representative samples from noisy posterior distributions.

Jeffreys Flow improves robustness of Boltzmann generators for rare event sampling.

problem Rare events and metastable trapping in sampling physical systems with rough energy landscapes.
method Introduces Jeffreys Flow, a robust generative framework using Parallel Tempering distillation and symmetric Jeffreys divergence to mitigate mode collapse and improve mode coverage.
result Minimizing Jeffreys divergence suppresses mode collapse and corrects inaccuracies in multi-modal distributions.

PTSD improves neural samplers by combining diffusion models and PT, enhancing efficiency.

problem Efficiency and correlation issues in neural samplers compared to PT.
method Sequential training of diffusion models across temperatures, combining high-temperature models for approximate lower-temperature samples.
result Significantly improved target evaluation efficiency, outperforming diffusion-based samplers.

Paper improves Bayesian neural learning efficiency and uncertainty quantification.

problem Challenges in convergence and scalability of MCMC techniques for Bayesian neural learning.
method Parallel tempering and Langevin-gradient information in Metropolis-Hastings proposals.
result Improves computational time and prediction/decision-making capabilities.

New method improves sampling from complex, multi-peaked distributions.

problem Sampling from high-dimensional, multimodal distributions using HMC.
method Combines tempered HMC with automatic tuning strategies.
result Demonstrates more effective scaling with dimension than adaptive methods.

Enhances sampling for complex hidden Markov models using ensemble MCMC.

problem Challenges in Bayesian inference for factorial hidden Markov models due to large latent variable space.
method Introduces ensemble MCMC with parallel tempering and genetic algorithm for efficient exploration.
result Improves sampling efficiency and mixing of existing samplers in various applications.

Restricted Boltzmann Machines (RBMs) are one of the fundamental building blocks of deep learning. Approximate maximum likelihood training of RBMs typically necessitates sampling from these models. In many training scenarios, computationally efficient Gibbs sampling procedures are crippled by poor mixing. In this work w…

2014-10-01abs ↗pdf ↗

New method improves deep neural network training by sampling nonlocal paths in hyperparameter space.

problem Training deep neural networks efficiently and avoiding overfitting.
method Optimizing over nonlocal paths in hyperparameter space using parallel tempering.
result Improved training speed and reduced overfitting, as shown by empirical tests.

Researchers study the geometric properties of a specific type of stable processes.

problem Understanding the information geometry of tempered stable processes.
method Derivation of α-divergence, Fisher information matrices, and α-connections.
result Obtained Fisher information matrices and α-connections for statistical manifolds.

Investigates tempered stable distributions and processes, including density transformations and parameter estimation.

problem Understanding the properties and applications of tempered stable distributions and processes.
method Analysis of limit distributions, parameter estimation, density transformations, and computation of pp-variation indices.
result Computed pp-variation indices for tempered stable processes and discussed exponential stock models driven by these processes.

The paper connects tempering and entropic mirror descent for sampling.

problem Sampling from a target distribution with known unnormalized density.
method Establishes the connection between tempering SMC and entropic mirror descent, deriving convergence rates and geometric insights.
result Tempering SMC iterates correspond to entropic mirror descent on the reverse KL divergence, providing new optimization perspectives.

We introduce a new distance metric for non-linear embeddings of Tempered Exponential Measures.

problem Non-linear embeddings of Tempered Exponential Measures (TEMs).
method Parameterization of finite discrete TEMs via Legendre functions, introducing tempered Hilbert co-simplex distance.
result Established a generalization of the Hilbert log cross-ratio simplex distance to a tempered Hilbert co-simplex distance.

A definition for elliptical tempered stable distribution, based on the characteristic function, have been explained which involve a unique spectral measure. This definition provides a framework for creating a connection between infinite divisible distribution, and particularly elliptical tempered stable distribution, w…

2014-08-14abs ↗pdf ↗

Geometric tempering fails for Langevin dynamics, proving convergence limits.

problem Proving convergence and limitations of geometric tempering for Langevin dynamics.
method Theoretical investigation of geometric tempering using Langevin dynamics.
result Geometric tempering can lead to exponential time convergence and poor functional inequalities.

Improved model-based estimation through tempered Bayes filter.

problem Improving predictive accuracy in partially-observable stochastic systems.
method Developed tempered Bayes filter combining likelihood and full posterior tempering.
result Tempered Bayes filter achieves improved predictive performance over the Bayes filter baseline.

Defines Schwartz and tempered functions on o-minimal manifolds.

problem Defining Schwartz and tempered functions on non-polynomially bounded o-minimal manifolds.
method Defining Schwartz and tempered functions on manifolds definable in polynomially bounded o-minimal structures, and showing classical properties hold.
result The theory of Schwartz and tempered functions can be constructed on manifolds definable in polynomially bounded o-minimal structures but not on non-polynomially bounded ones.

We offer new formulas for European option pricing under tempered stable processes.

problem Pricing European options under tempered stable processes.
method Series expansions for tempered stable densities and European option prices.
result Our formulas are hyperparameter-free and competitive with traditional methods.

A new multivariate distribution for modeling tails and dependence structures.

problem Modeling tails and dependence structures in multivariate data.
method Generalized Mixed Tempered Stable distribution, random number generation, estimation based on characteristic functions.
result Improved model fitting for multivariate data with better tail behavior and dependence structure.

Polynomial mixing times for simulated tempering in mixture sampling problems.

problem Sampling from mixtures of log-concave distributions with location shifts.
method Conductance decomposition applied to an auxiliary Markov chain on an augmented space.
result First polynomial-time guarantee for simulated tempering with MALA.

New framework uses tempered optimism to handle imperfect experts in online learning.

problem Challenges of implicit optimism in practical online learning environments.
method Introduces tempered optimism as a framework for online non-convex learning, modifies existing algorithms.
result Demonstrates tempered optimism as a fruitful paradigm for online non-convex learning.

Geometric tempering improves sampling from distributions, with exponential convergence rates.

problem Sampling from probability distributions using gradient flow dynamics.
method Geometric tempering of the target distribution in Wasserstein and Fisher-Rao gradient flows.
result Exponential convergence in continuous and discrete time for geometric tempering.

Investigates stock models using tempered stable processes for option pricing.

problem Analyzing option pricing in stock models driven by tempered stable processes.
method Investigates exponential stock models driven by tempered stable processes, providing existence of equivalent martingale measures and pricing formulae.
result Existence of equivalent martingale measures and pricing formulae for European call options.

New method estimates tempered stable Lévy models with high accuracy.

problem Estimating volatility and jump intensity of tempered stable Lévy processes.
method Iterative method combining Truncated Realized Quadratic Variations and small-time approximations.
result Method outperforms existing alternatives in various scenarios.

Paper approximates first passage time for tempered stable process for option pricing.

problem Pricing perpetual American options and barrier options using first passage time.
method Approximates characteristic function using martingale approach.
result Provides explicit or indirect numerical method for characteristic function of first passage time.

Bayesian classification improves with explicit aleatoric uncertainty.

problem Lack of aleatoric uncertainty representation in Bayesian classification.
method Explicitly account for aleatoric uncertainty using a Dirichlet observation model.
result Explicit aleatoric uncertainty improves performance of Bayesian neural networks.

Characterizes Lévy-driven Ornstein-Uhlenbeck processes linked to tempered stable distributions.

problem Understanding Lévy-driven Ornstein-Uhlenbeck processes and their properties.
method Characterizes the Lévy triplet and deduces transition laws for finite variation Ornstein-Uhlenbeck processes associated with tempered stable distributions.
result Provides algorithms for generating skeleton of Ornstein-Uhlenbeck processes related to exponentially-modulated tempered stable laws.

New theorem improves spectral gap for sampling from mixture distributions.

problem Sampling from multimodal distributions with simulated tempering.
method Introduced a decomposition theorem for the restricted spectral gap of simulated tempering.
result Lower bound on the restricted spectral gap for mixture distributions.

Geometrically realises restricted tempered representations of Lie groups.

problem Realising the restriction of tempered representations to maximal compact subgroups.
method Using Dirac operators on homogeneous spaces identified with coadjoint orbits.
result Explicit geometric expression for multiplicities of KK-types.