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.

168,695 papers · 148 categories

Trend · papers per month

1223 · Sep 202519922001200920172026
37 results for inverse-temperature

Study shows sample complexity for logistic regression with normal covariates.

problem Estimating parameters of logistic regression with normal design.
method Analyzes sample complexity in terms of dimension and inverse temperature.
result Shows two change-points in sample complexity curve based on inverse temperature.

Partition functions of probability distributions are important quantities for model evaluation and comparisons. We present a new method to compute partition functions of complex and multimodal distributions. Such distributions are often sampled using simulated tempering, which augments the target space with an auxiliar…

2016-03-07abs ↗pdf ↗

Estimates inverse temperature of Ising models with a single sample.

problem Estimating inverse temperature in truncated Ising models with hard constraints.
method Maximizing pseudolikelihood to estimate the inverse temperature.
result An estimator that is nearly O(n)O(n) time and O(Δ3/n)O(Δ^3/\sqrt{n})-consistent.

We investigate Ising model description of dynamics of stock price. The model is defined in near 2 dimensions, one dimension is time and another represents ensemble of stocks, and strength of response of investors to price change corresponds to inverse temperature of the system. At critical temperature, infinitely long …

2004-02-20abs ↗pdf ↗

A new sampler and temperature estimation method enable efficient learning of Boltzmann Machines.

problem Efficient learning of Boltzmann Machines (BMs) is challenging due to high training costs and difficulty in parallelization.
method Proposed a new Boltzmann sampler (Langevin SB, LSB) and an efficient method (Conditional Expectation Matching, CEM) for estimating inverse temperature.
result Established an efficient learning framework (Sampler-Adaptive Learning, SAL) for BMs with greater expressive power than Restricted Boltzmann Machines (RBMs).

Evaluation of the marginal likelihood plays an important role in model selection problems. The widely applicable Bayesian information criterion (WBIC) and singular Bayesian information criterion (sBIC) give approximations to the log marginal likelihood, which can be applied to both regular and singular models. When the…

2019-06-04abs ↗pdf ↗

The paper analyzes the InfoNCE loss under different temperature schedules using Langevin dynamics.

problem Understanding the dynamics of InfoNCE loss under fixed versus annealed temperature schedules.
method Modeling embedding evolution under Langevin dynamics on a compact Riemannian manifold, with theoretical guarantees for convergence.
result Slow logarithmic inverse-temperature schedules ensure convergence to globally optimal representations, while faster schedules risk suboptimal minima.

Estimate relaxation times in nonextensive systems using gradient flow for Tsallis entropy maximization.

problem Estimating relaxation times in financial market dynamics.
method Developing a method using EGF for maximizing Tsallis entropy.
result Longer relaxation times for nonextensive systems compared to Shannon entropy.

Algorithm learns Sherrington-Kirkpatrick model parameters at low temperatures.

problem Learning parameters of random graphical models at low temperatures.
method Multiplicative-weight update algorithm for polynomial time learning.
result Algorithm learns SK model parameters at βlognβ\leq \sqrt{\log n}.

fSGLD optimizes deep learning by favoring flat regions in the loss landscape.

problem Understanding and improving the behavior and generalization of deep learning algorithms.
method Flatness-Aware Stochastic Gradient Langevin Dynamics (fSGLD) that biases learning towards flat basins.
result fSGLD targets a flatness-biased Gibbs distribution with explicit excess risk guarantees.

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.

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.

The paper analyzes the dynamics of tokens in transformer models at moderate interaction levels.

problem Understanding the evolution of tokens in transformer models at moderate interaction levels.
method Modeling transformer models as a system of particles interacting in a mean-field way and studying the corresponding dynamics.
result Characterization and convergence of the limiting dynamics in different phases of the system.

AdaAnn optimizes annealing for efficient probability density approximation.

problem Efficiently approximating complex probability distributions with multiple modes.
method AdaAnn is an adaptive annealing scheduler that adjusts temperature increments based on KL divergence.
result AdaAnn improves computational efficiency in variational inference and parameter estimation.

We describe an adaptation of the simulated annealing algorithm to nonparametric clustering and related probabilistic models. This new algorithm learns nonparametric latent structure over a growing and constantly churning subsample of training data, where the portion of data subsampled can be interpreted as the inverse …

2014-02-22abs ↗pdf ↗

This work analyzes self-attention matrices using random matrix theory.

problem Understanding the theoretical behavior of self-attention layers in neural networks.
method Asymptotic spectral analysis of the attention matrix, Gaussian equivalence, and linearization.
result The singular value distribution of the attention matrix is asymptotically characterized by a linear model.

Improved similarity search in embeddings using InfoNCE loss.

problem Improving similarity search in embedding models trained by contrastive learning.
method Introduced a new continuity bound for InfoNCE loss via Gâteaux differentiation, preserving the averaging effect of negative samples.
result Demonstrated that the averaging effect of kk negative samples in InfoNCE loss carries over to stabilisation of generalisation error as kk grows.

Bayesian neural networks use temperature adjustments to improve predictive performance.

problem Lack of theoretical generalization guarantees for Bayesian neural networks.
method Temperature adjustments to balance likelihood and prior regularization.
result Improved predictive performance through temperature adjustments.

Learning capacity measures model complexity, correlating with test loss and sample size.

problem Understanding model complexity and its relation to test performance.
method Formal correspondence between thermodynamics and inference; learning capacity as a measure of effective dimensionality.
result Learning capacity correlates with test loss and is a small fraction of model parameters.

Bayesian models' singular fluctuation is shown to be akin to specific heat, influencing model complexity and generalization.

problem Understanding the thermodynamic interpretation of singular fluctuation in Bayesian models.
method Showed singular fluctuation as the curvature of Bayesian free energy and variance of log-likelihood observable under a Gibbs posterior.
result Singular fluctuation is the statistical analogue of specific heat, controlling model complexity and generalization.

A statistical model or a learning machine is called regular if the map taking a parameter to a probability distribution is one-to-one and if its Fisher information matrix is always positive definite. If otherwise, it is called singular. In regular statistical models, the Bayes free energy, which is defined by the minus…

2012-08-31abs ↗pdf ↗

Develops a new algorithm for estimating model parameters using interacting particle systems.

problem Estimating parameters of latent variable models.
method Interacting Particle Langevin Algorithm (IPLA) based on Langevin diffusion.
result Nonasymptotic optimisation error bounds for the estimator.

We characterize stationary solutions to McKean-Vlasov equations on the circle.

problem Stationary solutions of McKean-Vlasov equations on the circle.
method Exact equivalence to an infinite-dimensional quadratic system of equations over Fourier coefficients, leading to explicit characterization of stationary states.
result Analytic expressions for the emergence, form, and shape of bifurcations involving multiple Fourier modes, and connections with discontinuous phase transitions.