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.

168,657 papers · 148 categories

Trend · papers per month

173347520693 · Jun 202019922001200920172026
48 results for Low temperature sampling

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.

A new method combines AIS and SMCI for efficient evaluation of Ising models.

problem Efficiently evaluating expectations on Ising models under various temperatures.
method Combining Annealed Importance Sampling (AIS) and Spatial Monte Carlo Integration (SMCI).
result The proposed method performs efficiently in both high- and low-temperature regions.

The paper tackles sampling from Gibbs measures with constrained support, providing a sampling guarantee.

problem Sampling from Gibbs measures with constrained support, especially in the pre-asymptotic regime.
method Analyzing the spectral gap of Langevin dynamics to provide a non-asymptotic sampling guarantee.
result The low-temperature Gibbs distribution concentrates on a neighborhood of its mode in the pre-asymptotic regime.

The Gibbs algorithm's generalization error is bounded, improving with prior volume in low temperatures.

problem Bounding the generalization error of the Gibbs algorithm in low temperature regimes.
method Analyzes the Gibbs algorithm's performance, extending known high-temperature bounds to low-temperature scenarios.
result With high probability, the generalization error decreases with the total prior volume of similar hypotheses.

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}.

Improved diffusion models using energy distillation and sequential Monte Carlo.

problem Training instability and inferior performance in energy parameterized diffusion models.
method Introduced a novel training regime for energy functions through distillation of pre-trained diffusion models, and cast the sampling procedure as a Feynman Kac model.
result Demonstrated improved performance and new sampling techniques.

We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the log loss we use for training is replaced by a low temperature logarithm. By tuning the two temperatures we create loss functions that are non…

2019-06-08abs ↗pdf ↗

Investigates upsampling vs. upweighting for balanced training on skewed datasets.

problem Balancing training on heavily imbalanced datasets with scarce data.
method Theoretical and empirical analysis of upsampling and upweighting strategies.
result Upsampling and upweighting diverge under stochastic gradient descent, with upsampling leading to faster convergence but higher overfitting risk.

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.

Optimizes contrastive learning with individualized temperatures for better performance on imbalanced datasets.

problem The common practice of using a global temperature parameter ignores the varying semantic similarity across different anchor data.
method Proposes a new robust contrastive loss inspired by distributionally robust optimization (DRO) and an efficient stochastic algorithm for automatic temperature individualization.
result Our method automatically learns a suitable temperature for each sample, improving performance on imbalanced datasets.

CNN improves medium-range temperature forecasts with limited resources.

problem Limited computational resources for high-resolution temperature forecasts.
method CNN post-processing with ensemble NWP models for bias correction and spatial downscaling.
result High-resolution (5-km) surface temperature forecasts with lead times up to 5.5 days.

Researchers use Gaussian Process Regression to improve accuracy of a low-cost hot-wire anemometer.

problem Improving accuracy of low-cost hot-wire anemometers in varying temperatures.
method Probabilistic calibration using Gaussian Process Regression.
result The method provides good performance in estimating actual wind speeds, including uncertainty.

Power-SMC reduces inference latency for training-free LLM reasoning.

problem Training-free LLM reasoning with low latency.
method Power-SMC, a training-free Sequential Monte Carlo scheme targeting sequence-level power distribution.
result Power-SMC reduces inference latency from 16-28× to 1.4-3.3× over baseline decoding.

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 analyzes Gibbs and Langevin Monte Carlo for interpolation regime, showing generalization from low errors.

problem Analyzing Gibbs and Langevin Monte Carlo in overparameterized interpolation regime.
method Data-dependent bounds and stability under approximation with Langevin Monte Carlo.
result Generalization is signaled by small training errors in noisy regime, with bounds stable under approximation.

New method uses RBM flows to find critical temperatures in Ising models.

problem Detecting critical temperatures in RBM flows without model topology information.
method Iterative sampling from RBM mapped on Ising model temperature space using a neural network thermometer.
result Flow of RBM trained on Ising spin configurations approaches critical temperature around kBTc/J2.269k_B T_c / J \approx 2.269.

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 ↗

Improved logistic MoE with sigmoid gate shows better sample efficiency.

problem Improving sample efficiency in logistic MoE models.
method Comprehensive analysis of multinomial logistic MoE with modified sigmoid gate, incorporating temperature parameter and using Euclidean score.
result The sigmoid gate leads to lower sample complexity than softmax gate for both parameter and expert estimation.

CNN detects phase transitions in Potts models without prior knowledge.

problem Detecting phase transitions in qq-state Potts models using deep learning.
method Trained a deep CNN on Ising model spin configurations and temperatures, then tested on Potts model images.
result Deep CNN accurately detects phase transitions in Potts models, including high- and low-temperature regions.

Hyperfitting improves LLM generation quality by enhancing diversity, contrary to simple temperature scaling.

problem Improving open-ended generation quality of LLMs with minimal fine-tuning effort.
method Demonstrates that hyperfitting, a phenomenon where LLMs are fine-tuned to near-zero training loss, enhances generation quality and mitigates repetition.
result Hyperfitting is distinct from temperature scaling and involves a dynamic, context-dependent rank reordering mechanism in the final transformer block.

The study optimizes simulated annealing's cooling schedule for better performance.

problem Designing optimal cooling schedules for simulated annealing to improve its performance.
method Analyzed the cooling schedule's impact on simulated annealing's performance and provided sample and simulation complexity results.
result Optimal cooling schedules can be found with a small number of samples, improving the algorithm's runtime or success rate.

Enhances out-of-domain calibration of neural networks.

problem Improving calibration performance of deep neural networks in out-of-domain settings.
method Consistency-guided temperature scaling (CTS) that considers style and content consistency.
result Significantly enhances out-of-domain calibration performance.

Bayesian inference is used extensively to infer and to quantify the uncertainty in a field of interest from a measurement of a related field when the two are linked by a physical model. Despite its many applications, Bayesian inference faces challenges when inferring fields that have discrete representations of large d…

2019-07-22abs ↗pdf ↗

TemperatureGAN generates hourly atmospheric temperature data with high fidelity.

problem Generating accurate hourly atmospheric temperature data for climate risk assessment.
method Generative Adversarial Network (GAN) conditioned on months, locations, and time periods.
result TemperatureGAN produces high-fidelity hourly atmospheric temperature data with good spatial and temporal consistency.

The cold posterior effect is explored through PAC-Bayes bounds for small sample sizes.

problem The cold posterior effect in approximate Bayesian inference for small datasets.
method Investigation through PAC-Bayes generalization bounds, focusing on temperature parameter λ.
result The temperature parameter λ in PAC-Bayes bounds captures the cold posterior effect.

Contrastive learning adapts to data intrinsic dimensions, learning low-dimensional representations.

problem Learning high-dimensional representations from multi-modal data.
method Multi-modal contrastive learning with temperature optimization.
result Contrastive learning adapts to intrinsic dimensions of data, not specified dimensions.

Study convergence of simulated annealing in continuous and discrete settings.

problem Analyzing convergence rate of simulated annealing methods.
method Apply Eyring-Kramers law to prove polynomial decay of tail probabilities.
result Explicit rate of convergence for continuous and discrete simulated annealing.

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).

New method approximates sampling from smooth potential distributions using a vanishing penalty.

problem Sampling from smooth potential distributions on high-dimensional spaces.
method Penalized Langevin dynamics (PLD) with vanishing penalty.
result Established upper bound on Wasserstein-2 distance for PLD approximation.

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.

New method uses neural networks to efficiently approximate Bayesian inference for complex models.

problem Efficiently approximating Bayesian inference for complex models with varying temperatures.
method Fully amortized neural posterior estimator trained on a single forward pass.
result Achieves competitive posterior approximations across various temperatures and benchmarks.

New method uses birth-death process and exploration component to accelerate sampling from multimodal distributions.

problem Sampling from multimodal probability distributions efficiently.
method Combines birth-death process and exploration component to accelerate sampling.
result Proves exponential asymptotic convergence under mild assumptions.

Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are compact while the embeddings of samples of different categories are spread-out i…

2018-09-11abs ↗pdf ↗