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.

168,694 papers · 148 categories

Trend · papers per month

72145217289 · Jun 202019922001200920172026
48 results for Temperature Scaling

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.

Temperature scaling fails for distributions with class overlaps, while Mixup improves calibration.

problem Temperature scaling's performance degrades with class overlaps, leading to poor calibration.
method Identified temperature scaling's limitations and compared it with Mixup for calibration.
result Mixup significantly outperforms temperature scaling in calibration metrics with class overlaps.

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.

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.

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.

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.

Paper develops a new method to improve model calibration under distribution shifts.

problem Challenges in uncertainty quantification with different training and test distributions.
method Develops multi-domain temperature scaling to handle distribution shifts.
result Outperforms existing methods on in-distribution and out-of-distribution test sets.

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%.

New method calibrates classifier probabilities with guaranteed coverage.

problem Inaccurate probability estimates by classifiers in high-risk applications.
method Adaptive temperature scaling algorithm for conformal prediction.
result Improves calibration error measures and standard metrics across various tasks.

A theory explaining how deep learning works is yet to be developed. Previous work suggests that deep learning performs a coarse graining, similar in spirit to the renormalization group (RG). This idea has been explored in the setting of a local (nearest neighbor interactions) Ising spin lattice. We extend the discussio…

2020-02-07abs ↗pdf ↗

DSoftKI scales GP regression with full derivative observations.

problem Efficiently fitting and predicting full derivative observations in Gaussian Processes.
method Extends SoftKI by using local temperature vectors for interpolation, enabling encoding of local directional sensitivity.
result DSoftKI achieves accurate predictions and scales to larger datasets with full derivative observations.

New analysis shows temperature guarantees generalization in stochastic training.

problem Analyzing the generalization gap in stochastic training algorithms.
method Analyzing Langevin dynamics with positive temperature and bounding the generalization gap.
result Bounding the generalization gap by √(βE[L(θ_0)] + log(1/δ))/√N with probability 1-δ.

Paper studies convergence of Mean-Field GDA dynamics for MNE of continuous games.

problem Finding mixed Nash equilibria in continuous games.
method Two-scale Mean-Field Gradient Descent Ascent dynamics.
result Two-scale Mean-Field GDA converges exponentially to MNE without convexity assumptions.

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 ↗

LiST improves neural network robustness and calibration without manual tuning.

problem Developing robust and calibrated neural networks simultaneously.
method Lipschitz Scaling Training (LiST) that iteratively adjusts the global Lipschitz constant.
result LiST yields an out-of-the-box calibrated network with competitive accuracy and robustness.

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.

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 ↗

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.

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.

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 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.

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.

New bin-wise scaling methods improve prediction uncertainty calibration for machine learning.

problem Improving prediction uncertainty calibration for machine learning regression.
method Adaptations of Binwise Variance Scaling (BVS) with alternative loss functions and feature-based binning.
result Improved adaptivity and consistency in prediction uncertainty calibration.

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.

Over the last 23 years, the U.S. Securities and Exchange Commission has required over 34,000 companies to file over 165,000 annual reports. These reports, the so-called "Form 10-Ks," contain a characterization of a company's financial performance and its risks, including the regulatory environment in which a company op…

2016-12-29abs ↗pdf ↗

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}.

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.