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.

168,742 papers · 148 categories

Trend · papers per month

3775112149 · Jun 202019922001200920172026
48 results for normalized temperature-scaled cross-entropy

G-SimCLR improves unsupervised learning by clustering images into pseudo labels.

problem Improving unsupervised learning for image recognition.
method Proposes a method to cluster images into pseudo labels to batch images of the same category.
result Comparable performance enhancements on CIFAR10 and ImageNet datasets.

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.

Paper proposes ensemble distillation for well-calibrated structured prediction.

problem Well-calibrated predictions are hard to achieve in structured prediction.
method Ensemble distillation framework for structured prediction.
result Ensemble distillation produces well-calibrated models with similar performance and calibration benefits to ensembles.

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.

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.

Proposes a method to solve deep neural networks' local minimum problem.

problem Local minimum problem in deep neural networks training.
method Transforms cross-entropy loss into risk-averse error criterion, adjusts RSI, and uses convexity region.
result Trained deep learning machine is expected to be inside a global minimum's attraction basin.

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 method speeds up SoftMax normalization for embedding learning.

problem Efficiently learning distributed representations with SoftMax normalization.
method Proposes a linear-time heuristic approximation for mSoftMax(XYT){ m SoftMax}(XY^T), optimizing cross entropy.
result Achieves higher or comparable accuracy to existing methods with lower computational time.

Generative Cross-Entropy improves classification with fewer labels.

problem Limited sample efficiency of cross-entropy loss in data-scarce scenarios.
method Proposes Generative Cross-Entropy (GenCE), a new loss function that incorporates generative principles into a standard discriminative network.
result Generative Cross-Entropy outperforms traditional cross-entropy loss across various datasets and conditions.

This work includes a number of novel contributions for the multiple-source adaptation problem. We present new normalized solutions with strong theoretical guarantees for the cross-entropy loss and other similar losses. We also provide new guarantees that hold in the case where the conditional probabilities for the sour…

2018-05-20abs ↗pdf ↗

Quantum machine learning uses quantum cross entropy to minimize loss, but measurement loss affects this process.

problem Quantum machine learning's loss minimization through cross entropy is affected by measurement outcomes.
method Defined quantum cross entropy, proved its lower bounds, and investigated its relation to quantum fidelity and likelihood.
result Quantum cross entropy is lower-bounded by negative log-likelihood when derived from quantum data, but measurement outcomes can cause loss.

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.

Gradient descent on normalized networks reveals sparsity preferences.

problem Understanding the inductive bias of gradient descent on normalized neural nets.
method Analysis of gradient descent on weight-normalized smooth homogeneous neural nets, focusing on SWN and EWN.
result EWN causes weights to be updated in a way that prefers asymptotic relative sparsity.

The paper proves asymptotic normality for multinomial logistic regression on null covariates.

problem Classical asymptotic normality results fail in high-dimensional multinomial logistic models.
method Developed asymptotic normality and chi-square results for multinomial logistic MLE on null covariates.
result Validated new methodology to test feature significance in high-dimensional classification problems.

This paper examines how different decoding algorithms for LLMs align with various goals.

problem Consistency of decoding algorithms with different goals in LLMs.
method Analysis of greedy, lookahead, random sampling, and temperature-scaled random sampling algorithms.
result Random sampling is consistent with the true probability distribution, but other goals require optimal algorithms for specific probability distributions.

Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.

problem Improving metric learning performance without complex optimization schemes.
method Theoretical analysis linking cross-entropy to pairwise losses, showing cross-entropy as an upper bound and equivalent to mutual information maximization.
result Minimizing cross-entropy is equivalent to maximizing mutual information, leading to state-of-the-art performance.

Unified interpretation of softmax cross-entropy and negative sampling for knowledge graph embedding.

problem Lack of theoretical relationship between softmax cross-entropy and negative sampling loss functions in knowledge graph embedding.
method Used Bregman divergence to provide a unified interpretation of the two loss functions.
result Theoretical findings for fair comparison of softmax cross-entropy and negative sampling are derived.

Adaptive importance sampling for estimating point process statistics.

problem Estimating the expected value of a statistic of a locally stable point process.
method Adaptive importance sampling with Poisson point processes and cross-entropy minimization.
result The proposed estimator converges to the target value almost surely and is asymptotically normal.

Square loss performs comparably or better than cross-entropy in neural architectures for various tasks.

problem The superiority of cross-entropy loss over square loss in classification tasks is debated.
method Comparison of several neural architectures on NLP, ASR, and computer vision datasets using both loss functions.
result Square loss often produces better results in the majority of tasks, especially in NLP and ASR.

Theoretical analysis of cross-entropy loss functions and their robustness.

problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First HH-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.

The paper connects complex normalizing flows to Kähler-Ricci flows using geometric and statistical perspectives.

problem Understanding the relationship between complex normalizing flows and Kähler-Ricci flows.
method Develops connections between complex normalizing flows and Kähler-Ricci flows by relating the log determinant to Ricci curvature and using a Bayesian perspective.
result Reconciles the complex normalizing flow and Kähler-Ricci flow, showing they are related under certain conditions.

Study Transformer layers under cross-entropy training using mean field control.

problem Understanding the behavior of Transformer layers in cross-entropy training.
method Continuous-depth mean field control analysis, treating depth as time and layer parameters as controls.
result Derivation of a Pontryagin condition for the limiting population problem, involving the softmax residual.

Paper proposes a new loss function for conditional models using soft targets.

problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.

Softmax cross-entropy optimizes mutual information in neural networks.

problem Understanding the relationship between mutual information and classification neural networks.
method Demonstrated that optimizing softmax cross-entropy maximizes mutual information between inputs and labels.
result Softmax cross-entropy can approximate mutual information and highlight relevant image regions.

Paper proposes AXE loss for non-autoregressive machine translation, improving performance.

problem Challenges in training non-autoregressive models due to lack of autoregressive factors and cross entropy loss penalties.
method Proposes aligned cross entropy (AXE) loss function using a differentiable dynamic program for better word order alignment.
result AXE-based training improves performance on major WMT benchmarks and sets a new state of the art for non-autoregressive models.

Proposes squentropy loss for improved classification accuracy and model calibration.

problem Theoretical and empirical evidence for cross-entropy loss is lacking.
method Introduces squentropy loss as the sum of cross-entropy and average square loss over incorrect classes.
result Squentropy loss outperforms cross-entropy and rescaled square losses in classification accuracy and model calibration.

This paper investigates uncertainty calibration in multimodal large language models.

problem Challenges in properly calibrating uncertainty in multimodal large language models.
method Investigation of representative MLLMs across various scenarios, including visual fine-tuning and multimodal training.
result MLLMs tend to give answers rather than admit uncertainty, but this self-assessment improves with proper prompt adjustments.