paper-with-me

Papers

Uncertainty Estimation in Autoregressive Structured Prediction

2020-02-18 · ICLR 2021 1 · Andrey Malinin, Mark Gales

Uncertainty estimation is important for ensuring safety and robustness of AI systems. While most research in the area has focused on un-structured prediction tasks, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimation for autoregressive structured prediction tasks within a single unified and interpretable probabilistic ensemble-based framework. We consider: uncertainty estimation for sequence data at the token-level and complete sequence-level; interpretations for, and applications of, various measures of uncertainty; and discuss both the theoretical and practical challenges associated with obtaining them. This work also provides baselines for token-level and sequence-level error detection, and sequence-level out-of-domain input detection on the WMT'14 English-French and WMT'17 English-German translation and LibriSpeech speech recognition datasets.

📄 PDF Abstract BibTeX arXiv:2002.07650

Code (1)

iinemo/lm-polygraph pytorch

Tasks

Image ClassificationMachine TranslationPredictionspeech-recognitionSpeech RecognitionStructured PredictionTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction

2022-10-13 · Yuxuan Liu, Nikhil Mishra, Maximilian Sieb, Yide Shentu 외

3D bounding boxes are a widespread intermediate representation in many computer vision applications. However, predicting them is a challenging task, largely due to partial observability, which motivates the need for a st…

Prediction

Towards Generation-Efficient Uncertainty Estimation in Large Language Models

2026-05-07 · Mingcheng Zhu, Yu Liu, Tingting Zhu arxiv

Uncertainty estimation is important for deploying LLMs in high-stakes applications such as healthcare and finance, where hallucinations can appear fluent and plausible while being factually incorrect, making it difficult…

ProTerrain: Probabilistic Physics-Informed Rough Terrain World Modeling

2025-10-22 · Golnaz Raja, Ruslan Agishev, Miloš Prágr, Joni Pajarinen 외 arxiv

Uncertainty-aware robot motion prediction is crucial for downstream traversability estimation and safe autonomous navigation in unstructured, off-road environments, where terrain is heterogeneous and perceptual uncertain…

Trajectory ForecastingTrajectory Prediction

Fractal Autoregressive Depth Estimation with Continuous Token Diffusion

2026-03-16 · Jinchang Zhang, Xinrou Kang, Guoyu Lu arxiv

Monocular depth estimation can benefit from autoregressive (AR) generation, but direct AR modeling is hindered by the modality gap between RGB and depth, inefficient pixel-wise generation, and instability in continuous d…

Monocular Depth EstimationComputational Efficiency

Bayesian autoregressive spectral estimation

2021-10-05 · Alejandro Cuevas, Sebastián López, Danilo Mandic, Felipe Tobar

Autoregressive (AR) time series models are widely used in parametric spectral estimation (SE), where the power spectral density (PSD) of the time series is approximated by that of the \emph{best-fit} AR model, which is a…

Time SeriesTime Series Analysis