Search Results for author:
Found 22 papers, 8 papers with code
Similarity of Neural Networks with Gradients
A suitable similarity index for comparing learnt neural networks plays an important role in understanding the behaviour of the highly-nonlinear functions, and can provide insights on further theoretical analysis and empirical studies.
Automatic Discovery of Privacy-Utility Pareto Fronts
Differential privacy is a mathematical framework for privacy-preserving data analysis.
An Image is Worth Multiple Words: Learning Object Level Concepts using Multi-Concept Prompt Learning
To address this challenge, we introduce a framework for Multi-Concept Prompt Learning (MCPL), where multiple new "words" are simultaneously learned from a single sentence-image pair.
Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations
We conduct privacy audit experiments against 2 baseline models and utility experiments on 3 datasets to demonstrate the tradeoff between privacy and utility for varying values of epsilon on different task types.
HyperStream: a Workflow Engine for Streaming Data
This paper describes HyperStream, a large-scale, flexible and robust software package, written in the Python language, for processing streaming data with workflow creation capabilities.
$β^3$-IRT: A New Item Response Model and its Applications
Item Response Theory (IRT) aims to assess latent abilities of respondents based on the correctness of their answers in aptitude test items with different difficulty levels.
Improving Antibody Humanness Prediction using Patent Data
We investigate the potential of patent data for improving the antibody humanness prediction using a multi-stage, multi-loss training process.
Probabilistic Sensor Fusion for Ambient Assisted Living
There is a widely-accepted need to revise current forms of health-care provision, with particular interest in sensing systems in the home.
A Note on the Kullback-Leibler Divergence for the von Mises-Fisher distribution
We present a derivation of the Kullback Leibler (KL)-Divergence (also known as Relative Entropy) for the von Mises Fisher (VMF) Distribution in $d$-dimensions.
Continual Learning in Practice
This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives.
Privacy-preserving Active Learning on Sensitive Data for User Intent Classification
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance.
Facilitating Bayesian Continual Learning by Natural Gradients and Stein Gradients
Conventional models tend to forget the knowledge of previous tasks while learning a new task, a phenomenon known as catastrophic forgetting.
Distribution Calibration for Regression
We are concerned with obtaining well-calibrated output distributions from regression models.
Leveraging Hierarchical Representations for Preserving Privacy and Utility in Text
In this work, we explore word representations in Hyperbolic space as a means of preserving privacy in text.
Optimal Continual Learning has Perfect Memory and is NP-hard
Continual Learning (CL) algorithms incrementally learn a predictor or representation across multiple sequentially observed tasks.
Semi-Discriminative Representation Loss for Online Continual Learning
The use of episodic memory in continual learning has demonstrated effectiveness for alleviating catastrophic forgetting.
Interpretable Anomaly Detection with Mondrian P{ó}lya Forests on Data Streams
Anomaly detection at scale is an extremely challenging problem of great practicality.
Continual Density Ratio Estimation in an Online Setting
To the best of our knowledge, there is no existing method that can evaluate generative models in continual learning without storing samples from the original distribution.
Continual Density Ratio Estimation (CDRE): A new method for evaluating generative models in continual learning
We propose a new method Continual Density Ratio Estimation (CDRE), which can estimate density ratios between a target distribution of real samples and a distribution of samples generated by a model while the model is changing over time and the data of the target distribution is not available after a certain time point.
Discriminative Representation Loss (DRL): A More Efficient Approach than Gradient Re-Projection in Continual Learning
The use of episodic memories in continual learning has been shown to be effective in terms of alleviating catastrophic forgetting.
Unlocking the Heart Using Adaptive Locked Agnostic Networks
Supervised training of deep learning models for medical imaging applications requires a significant amount of labeled data.
Tackling Structural Hallucination in Image Translation with Local Diffusion
We hypothesize such hallucinations result from local OOD regions in the conditional images.
