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

98195293390 · Jun 202019922001200920172026
48 results for temperature parameter

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.

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}.

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.

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.

A new method selects optimal temperature for Bayesian Deep Learning.

problem Finding the optimal temperature for improving predictive performance in Bayesian Deep Learning.
method Data-driven approach to estimate temperature as a model parameter.
result Our method performs comparably to grid search but at a fraction of the cost.

GE-autoencoder identifies spontaneous symmetry breaking in systems.

problem Locating phase boundaries and identifying spontaneously broken symmetries in systems.
method Group-equivariant autoencoder using group theory to constrain parameters and learn invariant order parameters.
result GE-autoencoder accurately determines spontaneous symmetry breaking and estimates critical temperatures more efficiently.

We prove uniqueness of solutions to complex Monge-Ampère equations for small temperature.

problem Proving uniqueness of solutions to complex Monge-Ampère equations.
method Local and global analysis of bounded hyperconvex domains and compact complex manifolds.
result Uniqueness of solutions confirmed for small temperature parameters.

HET-XL improves heteroscedastic classifiers for large-scale image classification.

problem Scaling heteroscedastic classifiers to handle large numbers of classes and tuning the temperature hyperparameter.
method HET-XL, a heteroscedastic classifier with independent parameter count from the number of classes, learns the temperature hyperparameter directly from training data.
result HET-XL requires 14X fewer additional parameters and performs better than baseline heteroscedastic classifiers on large image classification datasets.

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.

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.

Bayesian framework quantifies uncertainty in portfolio temperature alignment.

problem Uncertainty in portfolio temperature alignment models.
method X-Degree Compatibility (XDC) approach with FaIR climate model, adaptive MCMC, deep learning emulator.
result Robust parametric uncertainty quantification for FaIR model.

MMD-Flagger detects hallucinations in LLMs by tracking MMD between outputs and temperature-generated counterparts.

problem Detecting hallucinations in large language models.
method Maximum Mean Discrepancy (MMD) to track the difference between model outputs and temperature-generated counterparts.
result MMD-Flagger detects most hallucinations by analyzing the shape of the MMD trajectory.

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.

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 develop a variant of multiclass logistic regression that is significantly more robust to noise. The algorithm has one weight vector per class and the surrogate loss is a function of the linear activations (one per class). The surrogate loss of an example with linear activation vector a\mathbf{a} and class cc has t…

2017-05-19abs ↗pdf ↗

Weather is a key production factor in agricultural crop production and at the same time the most significant and least controllable source of peril in agriculture. These effects of weather on agricultural crop production have triggered a widespread support for weather derivatives as a means of mitigating the risk assoc…

2018-08-13abs ↗pdf ↗

The paper models quanto weather and energy derivatives using Ornstein-Uhlenbeck processes and develops methods to hedge them.

problem Valuation and hedging of quanto derivatives on temperature and electricity.
method Developed a coupled model using Ornstein-Uhlenbeck processes and Conditional Least Square method for parameter estimation.
result Explicit and semi-explicit formulas for quanto options and hedging strategies are derived.

DISTANA improves weather prediction by inferring hidden factors from temperature data.

problem Inferring hidden factors in spatiotemporal processes without supervision.
method Enhanced DISTANA architecture for spatiotemporal data, active tuning for latent state inference.
result DISTANA achieves more accurate predictions than other methods, inferring hidden factors from temperature data.

Variational inference (VI) combined with data subsampling enables approximate posterior inference over large data sets, but suffers from poor local optima. We first formulate a deterministic annealing approach for the generic class of conditionally conjugate exponential family models. This approach uses a decreasing te…

2014-11-07abs ↗pdf ↗

A new topology design improves zero-shot classification performance in contrastive learning.

problem Improving zero-shot classification performance in contrastive visual-textual alignment.
method Proposed an alternative topology design using multiple class tokens and an oblique manifold with negative inner product.
result Improves zero-shot classification performance by an average of 6.1%.

Temperature scaling improves model uncertainty but not diversity in LLMs.

problem Improving the calibration and stochasticity of probabilistic models.
method Investigates theoretical properties of temperature scaling in classification and LLMs.
result Temperature scaling increases model uncertainty but not diversity in LLMs.

Study local sensitivity of HDD and CDD temperature derivatives prices.

problem Understanding how temperature derivatives prices change with small temperature changes.
method Analyzes sensitivity of HDD and CDD futures and options prices to temperature perturbations using a CAR process.
result Identifies the order of the CAR process and its impact on temperature derivatives prices.

Dual ML approach predicts peak temperatures in AFSD, improving process optimization.

problem Lack of understanding between process parameters and resulting microstructure in AFSD.
method Combines supervised machine learning and physics-informed neural networks.
result Ensemble techniques like gradient boosting outperform other SML methods in predicting peak temperatures.

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 ↗

Study reveals structural differences in financial networks near and far from crises using balance theory.

problem Understanding the complex behavior of stocks and their collective behavior in financial crises.
method Investigates financial networks by triplet interaction in the framework of balance theory, focusing on higher-order interactions.
result Formation of an ordered structure in crisis networks makes them resistant to disorder, with a critical temperature measuring crisis strength.

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.

This paper measures temperature in agent systems using volatility.

problem How to measure temperature in agent systems.
method Examined an agent system with two decision options in a news environment, established the measurement equation, and outlined the concept of temperature measurement.
result Illustrated a strategy for influencing average opinion in competing subsystems.

Attention temperature improves robustness of ICL in high-dimensional settings.

problem ICL robustness failure under distribution shift in high dimensions.
method Analyzed a Transformer with approximate softmax attention, derived a closed-form error expression, and showed optimal temperature minimizes error.
result Optimal attention temperature minimizes ICL generalization error under distribution shift.

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.

Trends in terrestrial temperature variability are perhaps more relevant for species viability than trends in mean temperature. In this paper, we develop methodology for estimating such trends using multi-resolution climate data from polar orbiting weather satellites. We derive two novel algorithms for computation that …

2018-05-18abs ↗pdf ↗

The paper analyzes extreme temperature forecasting using machine learning models.

problem Forecasting extreme temperatures in U.S. cities.
method Auto-Regressive Integrated Moving Average, Exponential Smoothing, Multilayer Perceptrons, Gaussian Processes.
result Multilayer Perceptrons were found to be the most effective approach for forecasting extreme temperatures.

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.

Deep learning model predicts European weather parameters.

problem Ensemble weather prediction using deep learning.
method Conditional deep convolutional generative adversarial network (GAN) and Monte-Carlo dropout.
result Forecast skill for geopotential height and two-meter temperature is good, but precipitation is challenging.

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.