paper-with-me

홈 › Papers

ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space

2025-07-14 · Shim Soon Yong

We introduce a novel classification framework, ZClassifier, that replaces conventional deterministic logits with diagonal Gaussian-distributed logits. Our method simultaneously addresses temperature scaling and manifold approximation by minimizing the Kullback-Leibler (KL) divergence between the predicted Gaussian distributions and a unit isotropic Gaussian. This unifies uncertainty calibration and latent control in a principled probabilistic manner, enabling a natural interpretation of class confidence and geometric consistency. Experiments on CIFAR-10 show that ZClassifier improves over softmax classifiers in robustness, calibration, and latent separation.

📄 PDF Abstract BibTeX arXiv:2507.10638

Code (1)

ShimSoonYong/ZClassifier 공식 구현 pytorch

Tasks

Out of Distribution (OOD) Detection

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

2019-06-08 · NeurIPS 2019 12 · Ehsan Amid, Manfred K. Warmuth, Rohan Anil, Tomer Koren

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 …

Tethered Reasoning: Decoupling Entropy from Hallucination in Quantized LLMs via Manifold Steering

2026-02-06 · Craig Atkinson arxiv

Quantized language models face a fundamental dilemma: low sampling temperatures yield repetitive, mode-collapsed outputs, while high temperatures (T > 2.0) cause trajectory divergence and semantic incoherence. We present…

A Graph-based approach to derive the geodesic distance on Statistical manifolds: Application to Multimedia Information Retrieval

2021-06-26 · Zakariae Abbad, Ahmed Drissi El Maliani, Said Ouatik El Alaoui, Mohammed El Hassouni

In this paper, we leverage the properties of non-Euclidean Geometry to define the Geodesic distance (GD) on the space of statistical manifolds. The Geodesic distance is a real and intuitive similarity measure that is a g…

Information RetrievalRetrieval

Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking

2026-08-20 · Yansen Han, Shengyi Liao, Yuanxing Zhang, Pengfei Wan 외 arxiv

Preference optimization is a standard alignment method for generative models, yet extending it to continuous-time dynamics remains non-trivial. In flow matching, reward-driven updates modify transport trajectories withou…

Two-temperature logistic regression based on the Tsallis divergence

2017-05-19 · Ehsan Amid, Manfred K. Warmuth, Sriram Srinivasan

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 cla…

regressionVocal Bursts Valence Prediction