280 citations · 1.1k across the 43 of their papers we have counts for
21 papers · 1 filter
ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
Hee Suk Yoon, Joshua Tian Jin Tee, Eunseop Yoon +4
Studies have shown that modern neural networks tend to be poorly calibrated due to over-confident predictions. Traditionally, post-processing methods have been used to calibrate th…
Calibrating Transformers via Sparse Gaussian Processes
Wenlong Chen, Yingzhen Li
Transformer models have achieved profound success in prediction tasks in a wide range of applications in natural language processing, speech recognition and computer vision. Extend…
Scalable Infomin Learning
Yanzhi Chen, Weihao Sun, Yingzhen Li +1
The task of infomin learning aims to learn a representation with high utility while being uninformative about a specified target, with the latter achieved by minimising the mutual…
Markovian Gaussian Process Variational Autoencoders
Harrison Zhu, Carles Balsells Rodas, Yingzhen Li
Sequential VAEs have been successfully considered for many high-dimensional time series modelling problems, with many variant models relying on discrete-time mechanisms such as rec…
Repairing Neural Networks by Leaving the Right Past Behind
Ryutaro Tanno, Melanie F. Pradier, Aditya Nori +1
Prediction failures of machine learning models often arise from deficiencies in training data, such as incorrect labels, outliers, and selection biases. However, such data points t…
Learning Neural Set Functions Under the Optimal Subset Oracle
Zijing Ou, Tingyang Xu, Qinliang Su +3
Learning neural set functions becomes increasingly more important in many applications like product recommendation and compound selection in AI-aided drug discovery. The majority o…
A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging
Thomas Henn, Yasukazu Sakamoto, Clément Jacquet +8
Machine learning models commonly exhibit unexpected failures post-deployment due to either data shifts or uncommon situations in the training environment. Domain experts typically…
Interpreting diffusion score matching using normalizing flow
Wenbo Gong, Yingzhen Li
Scoring matching (SM), and its related counterpart, Stein discrepancy (SD) have achieved great success in model training and evaluations. However, recent research shows their limit…
Contextual HyperNetworks for Novel Feature Adaptation
Angus Lamb, Evgeny Saveliev, Yingzhen Li +7
While deep learning has obtained state-of-the-art results in many applications, the adaptation of neural network architectures to incorporate new output features remains a challeng…
Active Slices for Sliced Stein Discrepancy
Wenbo Gong, Kaibo Zhang, Yingzhen Li +1
Sliced Stein discrepancy (SSD) and its kernelized variants have demonstrated promising successes in goodness-of-fit tests and model learning in high dimensions. Despite their theor…
Reinforcement Learning with Efficient Active Feature Acquisition
Haiyan Yin, Yingzhen Li, Sinno Jialin Pan +2
Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gath…
A Study on Efficiency in Continual Learning Inspired by Human Learning
Philip J. Ball, Yingzhen Li, Angus Lamb +1
Humans are efficient continual learning systems; we continually learn new skills from birth with finite cells and resources. Our learning is highly optimized both in terms of capac…
Interpreting Spatially Infinite Generative Models
Chaochao Lu, Richard E. Turner, Yingzhen Li +1
Traditional deep generative models of images and other spatial modalities can only generate fixed sized outputs. The generated images have exactly the same resolution as the traini…
Meta-Learning Divergences of Variational Inference
Ruqi Zhang, Yingzhen Li, Christopher De Sa +2
Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability. Crucial to the performance of VI i…
Sliced Kernelized Stein Discrepancy
Wenbo Gong, Yingzhen Li, José Miguel Hernández-Lobato
Kernelized Stein discrepancy (KSD), though being extensively used in goodness-of-fit tests and model learning, suffers from the curse-of-dimensionality. We address this issue by pr…
A Causal View on Robustness of Neural Networks
Cheng Zhang, Kun Zhang, Yingzhen Li
We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measuremen…
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li +4
The ability for policies to generalize to new environments is key to the broad application of RL agents. A promising approach to prevent an agent's policy from overfitting to a lim…
Interpretable Outcome Prediction with Sparse Bayesian Neural Networks in Intensive Care
Hiske Overweg, Anna-Lena Popkes, Ari Ercole +4
Clinical decision making is challenging because of pathological complexity, as well as large amounts of heterogeneous data generated as part of routine clinical care. In recent yea…
Disentangled Sequential Autoencoder
Yingzhen Li, Stephan Mandt
We present a VAE architecture for encoding and generating high dimensional sequential data, such as video or audio. Our deep generative model learns a latent representation of the…
Are Generative Classifiers More Robust to Adversarial Attacks?
Yingzhen Li, John Bradshaw, Yash Sharma
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively develo…
Dropout Inference in Bayesian Neural Networks with Alpha-divergences
Yingzhen Li, Yarin Gal
To obtain uncertainty estimates with real-world Bayesian deep learning models, practical inference approximations are needed. Dropout variational inference (VI) for example has bee…