paper-with-me

홈 › Papers

Midpoint Regularization: from High Uncertainty Training to Conservative Classification

2021-06-26 · Hongyu Guo

Label Smoothing (LS) improves model generalization through penalizing models from generating overconfident output distributions. For each training sample the LS strategy smooths the one-hot encoded training signal by distributing its distribution mass over the non-ground truth classes. We extend this technique by considering example pairs, coined PLS. PLS first creates midpoint samples by averaging random sample pairs and then learns a smoothing distribution during training for each of these midpoint samples, resulting in midpoints with high uncertainty labels for training. We empirically show that PLS significantly outperforms LS, achieving up to 30% of relative classification error reduction. We also visualize that PLS produces very low winning softmax scores for both in and out of distribution samples.

📄 PDF Abstract BibTeX arXiv:2106.13913

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationVocal Bursts Intensity Prediction

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

Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds

2026-03-06 · Debashis Chatterjee arxiv

Offline reinforcement learning (RL) aims to learn decision policies from a fixed batch of logged transitions, without additional environment interaction. Despite remarkable empirical progress, offline RL remains fragile …

Reinforcement LearningOffline RL

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization

2023-09-03 · Uri Gadot, Esther Derman, Navdeep Kumar, Maxence Mohamed Elfatihi 외

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from that set, RMDPs add…

Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction

2025-09-23 · Huanxin Sheng, Xinyi Liu, Hangfeng He, Jieyu Zhao 외 arxiv

LLM-as-a-judge has become a promising paradigm for using large language models (LLMs) to evaluate natural language generation (NLG), but the uncertainty of its evaluation remains underexplored. This lack of reliability m…

Midpoint Generative Models

2026-05-28 · Daniil Shlenskii, Nikita Gushchin, Lev Novitskiy, Dmitry V. Dylov 외 arxiv

We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interpolation: when the two endpoint distribut…

Improved Label Design for Timing Synchronization in OFDM Systems against Multi-path Uncertainty

2023-07-19 · Chaojin Qing, Shuhai Tang, Na Yang, Chuangui Rao 외

Timing synchronization (TS) is vital for orthogonal frequency division multiplexing (OFDM) systems, which makes the discrete Fourier transform (DFT) window start at the inter-symbol-interference (ISI)-free region. Howeve…