Search Results for author:
Found 62 papers, 25 papers with code
The Systems Engineering Approach in Times of Large Language Models
Using Large Language Models (LLMs) to address critical societal problems requires adopting this novel technology into socio-technical systems.
Towards One Model for Classical Dimensionality Reduction: A Probabilistic Perspective on UMAP and t-SNE
This paper shows that dimensionality reduction methods such as UMAP and t-SNE, can be approximately recast as MAP inference methods corresponding to a model introduced in ProbDR, that describes the graph Laplacian (an estimate for the precision/inverse covariance) matrix using a Wishart distribution, with a mean given by a non-linear covariance function evaluated on the latents.
Scalable Amortized GPLVMs for Single Cell Transcriptomics Data
Dimensionality reduction is crucial for analyzing large-scale single-cell RNA-seq data.
Self-sustaining Software Systems (S4): Towards Improved Interpretability and Adaptation
S4 builds knowledge loops between all available knowledge sources that define modern software systems to improve their interpretability and adaptability.
Automated discovery of trade-off between utility, privacy and fairness in machine learning models
Thus the trade-off between fairness, privacy and performance of ML models emerges, and practitioners need a way of quantifying this trade-off to enable deployment decisions.
Causal fault localisation in dataflow systems
Dataflow computing was shown to bring significant benefits to multiple niches of systems engineering and has the potential to become a general-purpose paradigm of choice for data-driven application development.
Dimensionality Reduction as Probabilistic Inference
Dimensionality reduction (DR) algorithms compress high-dimensional data into a lower dimensional representation while preserving important features of the data.
Dataflow graphs as complete causal graphs
Component-based development is one of the core principles behind modern software engineering practices.
AI for Science: An Emerging Agenda
This report summarises the discussions from the seminar and provides a roadmap to suggest how different communities can collaborate to deliver a new wave of progress in AI and its application for scientific discovery.
Real-world Machine Learning Systems: A survey from a Data-Oriented Architecture Perspective
The survey shows the design decisions of the systems and the requirements these satisfy.
Ice Core Dating using Probabilistic Programming
Ice cores record crucial information about past climate.
Modelling Technical and Biological Effects in scRNA-seq data with Scalable GPLVMs
Single-cell RNA-seq datasets are growing in size and complexity, enabling the study of cellular composition changes in various biological/clinical contexts.
Modeling the Machine Learning Multiverse
Amid mounting concern about the reliability and credibility of machine learning research, we present a principled framework for making robust and generalizable claims: the multiverse analysis.
The Effect of Task Ordering in Continual Learning
Connecting to the field of curriculum learning, we show that the effect of task ordering can be exploited to modify continual learning performance, and present a simple approach for doing so.
An Empirical Evaluation of Flow Based Programming in the Machine Learning Deployment Context
Data Oriented Architecture (DOA) is an emerging approach that can support data scientists and software developers when addressing such challenges.
Scalable Bigraphical Lasso: Two-way Sparse Network Inference for Count Data
Unfortunately, the original Bigraphical Lasso algorithm is not applicable in case of large p and n due to memory requirements.
Generalised Gaussian Process Latent Variable Models (GPLVM) with Stochastic Variational Inference
We show how this framework is compatible with different latent variable formulations and perform experiments to compare a suite of models.
Bayesian Learning via Neural Schrödinger-Föllmer Flows
In this work we explore a new framework for approximate Bayesian inference in large datasets based on stochastic control (i. e. Schr\"odinger bridges).
Emulation of physical processes with Emukit
Decision making in uncertain scenarios is an ubiquitous challenge in real world systems.
Behavioral Experiments for Understanding Catastrophic Forgetting
In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too.
Inconsistency in Conference Peer Review: Revisiting the 2014 NeurIPS Experiment
Further, with seven years passing since the experiment we find that for \emph{accepted} papers, there is no correlation between quality scores and impact of the paper as measured as a function of citation count.
Towards better data discovery and collection with flow-based programming
Our main conclusion is that FBP shows great potential for providing data-centric infrastructural benefits for deployment of ML.
Solving Schrödinger Bridges via Maximum Likelihood
The Schr\"odinger bridge problem (SBP) finds the most likely stochastic evolution between two probability distributions given a prior stochastic evolution.
Challenges in Deploying Machine Learning: a Survey of Case Studies
In recent years, machine learning has transitioned from a field of academic research interest to a field capable of solving real-world business problems.
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
The evidence lower bound of the marginal log-likelihood of empirical Bayes decomposes as a sum of local KL divergences between the variational posterior and the true posterior on the query set of each task.
Ranked #13 on
Few-Shot Image Classification
on CIFAR-FS 5-way (1-shot)
Differentially Private Regression and Classification with Sparse Gaussian Processes
We experiment with the use of inducing points to provide a sparse approximation and show that these can provide robust differential privacy in outlier areas and at higher dimensions.
Modular Deep Probabilistic Programming
A probabilistic module consists of a set of random variables with associated probabilistic distributions and dedicated inference methods.
Variational Information Distillation for Knowledge Transfer
We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10.
Data Science and Digital Systems: The 3Ds of Machine Learning Systems Design
Machine learning solutions, in particular those based on deep learning methods, form an underpinning of the current revolution in "artificial intelligence" that has dominated popular press headlines and is having a significant influence on the wider tech agenda.
Transferring Knowledge across Learning Processes
Approaches that transfer information contained only in the final parameters of a source model will therefore struggle.
Auto-Differentiating Linear Algebra
Development systems for deep learning (DL), such as Theano, Torch, TensorFlow, or MXNet, are easy-to-use tools for creating complex neural network models.
Gaussian Process Latent Force Models for Learning and Stochastic Control of Physical Systems
This article is concerned with learning and stochastic control in physical systems which contain unknown input signals.
Preferential Bayesian Optmization
We present a new framework for this scenario that we call Preferential Bayesian Optimization (PBO) and that allows to find the optimum of a latent function that can only be queried through pairwise comparisons, so-called duels.
Efficient Modeling of Latent Information in Supervised Learning using Gaussian Processes
Often in machine learning, data are collected as a combination of multiple conditions, e. g., the voice recordings of multiple persons, each labeled with an ID.
Living Together: Mind and Machine Intelligence
In this paper we consider the nature of the machine intelligences we have created in the context of our human intelligence.
Preferential Bayesian Optimization
Bayesian optimization (BO) has emerged during the last few years as an effective approach to optimizing black-box functions where direct queries of the objective are expensive.
Manifold Alignment Determination: finding correspondences across different data views
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities.
The Emergence of Organizing Structure in Conceptual Representation
While this approach can learn intuitive organizations, including a tree for animals and a ring for the color circle, it assumes a strong inductive bias that considers only these particular forms, and each form is explicitly provided as initial knowledge.
Differentially Private Gaussian Processes
A major challenge for machine learning is increasing the availability of data while respecting the privacy of individuals.
Chained Gaussian Processes
Gaussian process models are flexible, Bayesian non-parametric approaches to regression.
Multi-view Learning as a Nonparametric Nonlinear Inter-Battery Factor Analysis
Inter-battery factor analysis extends this notion to multiple views of the data.
Recurrent Gaussian Processes
We define Recurrent Gaussian Processes (RGP) models, a general family of Bayesian nonparametric models with recurrent GP priors which are able to learn dynamical patterns from sequential data.
GLASSES: Relieving The Myopia Of Bayesian Optimisation
We present GLASSES: Global optimisation with Look-Ahead through Stochastic Simulation and Expected-loss Search.
Semi-described and semi-supervised learning with Gaussian processes
In this paper we refer to this task as "semi-described learning".
Batch Bayesian Optimization via Local Penalization
The approach assumes that the function of interest, $f$, is a Lipschitz continuous function.
Bayesian Optimization for Synthetic Gene Design
We address the problem of synthetic gene design using Bayesian optimization.
Nested Variational Compression in Deep Gaussian Processes
Deep Gaussian processes provide a flexible approach to probabilistic modelling of data using either supervised or unsupervised learning.
Metrics for Probabilistic Geometries
We investigate the geometrical structure of probabilistic generative dimensionality reduction models using the tools of Riemannian geometry.
Variational Inference for Uncertainty on the Inputs of Gaussian Process Models
The Gaussian process latent variable model (GP-LVM) provides a flexible approach for non-linear dimensionality reduction that has been widely applied.
Fast nonparametric clustering of structured time-series
In this publication, we combine two Bayesian non-parametric models: the Gaussian Process (GP) and the Dirichlet Process (DP).
Gaussian Processes for Big Data
We introduce stochastic variational inference for Gaussian process models.
Fast Variational Inference in the Conjugate Exponential Family
We present a general method for deriving collapsed variational inference algorithms for probabilistic models in the conjugate exponential family.
Variational Gaussian Process Dynamical Systems
Our work builds on recent variational approximations for Gaussian process latent variable models to allow for nonlinear dimensionality reduction simultaneously with learning a dynamical prior in the latent space.
Linear Latent Force Models using Gaussian Processes
Purely data driven approaches for machine learning present difficulties when data is scarce relative to the complexity of the model or when the model is forced to extrapolate.
Kernels for Vector-Valued Functions: a Review
Kernel methods are among the most popular techniques in machine learning.
Switched Latent Force Models for Movement Segmentation
Latent force models encode the interaction between multiple related dynamical systems in the form of a kernel or covariance function.
Sparse Convolved Gaussian Processes for Multi-output Regression
We present a sparse approximation approach for dependent output Gaussian processes (GP).
Accelerating Bayesian Inference over Nonlinear Differential Equations with Gaussian Processes
We demonstrate the speed and statistical accuracy of our approach using examples of both ordinary and delay differential equations, and provide a comprehensive comparison with current state of the art methods.
Efficient Sampling for Gaussian Process Inference using Control Variables
We describe an efficient Markov chain Monte Carlo algorithm for sampling from the posterior process of the GP model.
