PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Yarin Gal

6 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics

    2017 · arXiv (Cornell University)

    Numerous deep learning applications benefit from multi-task learning with multiple regression and classification objectives. In this paper we make the observation that the performance of such systems is strongly dependent on the relative weighting between …

  2. Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam

    2018 · arXiv (Cornell University)

    Uncertainty computation in deep learning is essential to design robust and reliable systems. Variational inference (VI) is a promising approach for such computation, but requires more effort to implement and execute compared to maximum-likelihood methods. …

  3. On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes

    2021 · International Conference on Machine Learning

    We show that the gradient estimates used in training Deep Gaussian Processes (DGPs) with importance-weighted variational inference are susceptible to signal-to-noise ratio (SNR) issues. Specifically, we show both theoretically and via an extensive empirical evaluation …

  4. Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

    2022 · arXiv (Cornell University)

    Bayesian deep learning seeks to equip deep neural networks with the ability to precisely quantify their predictive uncertainty, and has promised to make deep learning more reliable for safety-critical real-world applications. Yet, existing Bayesian deep …

  5. CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models

    2022 · arXiv (Cornell University)

    Users often ask dialogue systems ambiguous questions that require clarification. We show that current language models rarely ask users to clarify ambiguous questions and instead provide incorrect answers. To address this, we introduce CLAM: a …

  6. BatchGFN: Generative Flow Networks for Batch Active Learning

    2023 · arXiv (Cornell University)

    We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward. With an appropriate reward function to quantify the …