![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Siddharth Swaroop (University of Cambridge).
Wednesday 11 March 2020, 11:00-12:30
Engineering Department, CBL Room BE-438
Contact: No managers listed
0 upcoming talks View 135 archived talks
Machine Learning Reading Group @ CUED
Federated Learning
Machine Learning Reading Group @ CUED
Self-Supervised Representation Learning
Machine Learning Reading Group @ CUED
Kernel Mean Embeddings
Machine Learning Reading Group @ CUED
Neural Tangent Kernel
Machine Learning Reading Group @ CUED
Scalable Gaussian Processes
Machine Learning Reading Group @ CUED
Probabilistic Programming
Machine Learning Reading Group @ CUED
Neural Attention
Machine Learning Reading Group @ CUED
Equivariance and Symmetries in CNNs
Machine Learning Reading Group @ CUED
Hyperparameter Optimisation
Machine Learning Reading Group @ CUED
Meta-Learning or "Learning To Learn"
Machine Learning Reading Group @ CUED
Hamiltonian Monte Carlo for Hierarchical Models
Machine Learning Reading Group @ CUED
Particle MCMC
Machine Learning Reading Group @ CUED
Stochastic Differential Equations
Machine Learning Reading Group @ CUED
Generalisation in neural networks
Machine Learning Reading Group @ CUED
An Overview of Normalizing Flows
Machine Learning Reading Group @ CUED
Sampling as Optimization
Machine Learning Reading Group @ CUED
Implicit Variational Inference
Machine Learning Reading Group @ CUED
Continual Learning: Definitions, Benchmarks, and Approaches
Machine Learning Reading Group @ CUED
Causal Inference and Causal Reinforcement Learning
Machine Learning Reading Group @ CUED
Generative models for few-shot prediction tasks
Machine Learning @ CUED
Learning with Memory Embeddings
Machine Learning @ CUED
Discriminative Embeddings of Latent Variable Models for Structured Data
Machine Learning @ CUED
Modeling the Dynamics of Online Learning Activity
Machine Learning @ CUED
Developments in Exact Inference in Graphical Models
Machine Learning @ CUED
Approximation strategies for structure learning in Bayesian networks
β οΈ Note: via Skype!
Machine Learning @ CUED
Variational inference for scalable Gaussian process approximations
Machine Learning @ CUED
Novel MCMC and SMC schemes for Poisson-Kingman Bayesian Nonparametric mixture models
Machine Learning @ CUED
Turing: Rejuvenating Probabilistic Programming in Julia
Machine Learning @ CUED
Towards Weaker Supervision and Simpler Pipelines in Speech Recognition
Machine Learning @ CUED
Sum-Product Networks for Probabilistic Modeling
Machine Learning @ CUED
MLE-Struct: Bethe Learning of Graphical Models
Machine Learning @ CUED
Inference and Learning in the Anglican Probabilistic Programming System
Machine Learning @ CUED
Unsupervised Risk Estimation with only Structural Assumptions
Machine Learning @ CUED
A more Automated Statistician
Machine Learning @ CUED
General Reinforcement Learning
Machine Learning @ CUED
Inference of a partially observed kinetic Ising model
Machine Learning @ CUED
Meta-Bayesian Analysis
Machine Learning @ CUED
Efficient Inference and Learning with Intractable Posteriors? Yes, Please.
Machine Learning @ CUED
Efficient multi-task Gaussian process models for genome-wide association studies
Machine Learning @ CUED
Harmonic Exponential Families and Group-Equivariant Convolution Networks
Machine Learning @ CUED
Higher Order Fused Regularization for Supervised Learning with Grouped Parameters
Machine Learning @ CUED
A-Star Sampling Review
Machine Learning @ CUED
Convex Factorization Machines
Machine Learning @ CUED
Belief and Truth in Hypothesised Behaviours
Machine Learning @ CUED
Training and Understanding Deep Neural Networks for Robotics, Design, and Perception
Machine Learning @ CUED
Information-Theoretic Bounded Rationality
Machine Learning @ CUED
The limits of MAP inference by MWSS on perfect graphs
Machine Learning @ CUED
Scalable Gaussian Processes for Scientific Discovery
Machine Learning @ CUED
MCMC for non-linear state space models using ensembles of latent sequences
β οΈ (via Skype!)
Machine Learning @ CUED
Gradient-based hyperparameter optimization through reversible learning
Machine Learning @ CUED
Rich Component Analysis
Machine Learning @ CUED
A new MCMC hybrid scheme for Poisson-Kingman Bayesian Nonparametric mixture models
Machine Learning @ CUED
Modeling Confounding by Half-Sibling Regression
β οΈ SHORT TALK (20 minutes)
Machine Learning @ CUED
Extreme Classification: A New Paradigm for Ranking & Recommendation
Machine Learning @ CUED
Convex and non-convex worlds in machine learning
Machine Learning @ CUED
Explaining Non-Linear Classifier Decisions with application to Deep Learning
Machine Learning @ CUED
Deep Gaussian processes and variational propagation of uncertainty
Machine Learning @ CUED
Unsupervised Learning with Latent Variable Models
Machine Learning @ CUED
Unsupervised Learning with Latent Variable Models
Machine Learning @ CUED
Structural Markov laws / Geometry and HMC
Machine Learning @ CUED
Do Deep Nets Really Need to be Deep?
Machine Learning @ CUED
Title to be confirmed
Machine Learning @ CUED
Inference for infinite mixture models and Gaussian Process mixtures of experts using simple approximate MAP Inference
Machine Learning @ CUED
Evolutionary dynamics in a continuous public goods game
Machine Learning @ CUED
An introduction to the Mondrian Process
Machine Learning @ CUED
Population Inference for Functional Brain Connectivity
Machine Learning @ CUED
Probabilistic approaches to understanding bird conversations
Machine Learning @ CUED
A Tutorial on Probabilistic Programming
Machine Learning @ CUED
New Methods in Bayesian Optimization for Machine Learning
Machine Learning @ CUED
Local Deep Kernel Learning for Efficient Non-linear SVM Prediction
Machine Learning @ CUED
Unsupervised Many-to-many Object Matching
Machine Learning @ CUED
Probabilistic Numerics - a snapshot of an emerging community
Machine Learning @ CUED
Bayesian inference for integer-valued LΓ©vy processes with Non-Gaussian Ornstein-Uhlenbeck volatility modelling
β οΈ short talk (30 mins) - NOTE TIME CHANGE
Machine Learning @ CUED
Density Estimation in Infinite Dimensional Exponential Families
Machine Learning @ CUED
Stable Poisson-Kingman species sampling priors generated by general ordered size biased generalized gamma mixing distributions
Machine Learning @ CUED
Probabilistic computing applications: BayesDB and stochastic digital circuits
Machine Learning @ CUED
Probabilistic computing for Bayesian inference
Machine Learning @ CUED
Machine Learning and Order Book Dynamics
Machine Learning @ CUED
Policy Evaluation with Temporal Differences
Machine Learning @ CUED
Matrix Means, Distances, Kernels, and Geometric Optimization
Machine Learning @ CUED
Learning to Learn for Structured Sparsity
Machine Learning @ CUED
Bayesian nonparametric dynamic-clustering and genetic imputation
Machine Learning @ CUED
Bayesian canonical correlation analysis
Machine Learning @ CUED
Cambridge - Tuebingen PhD Applicant Talks (via Skype)
β οΈ Interview talks via Skype
Machine Learning @ CUED
Generative probabilistic programming: applications and new ideas
Machine Learning @ CUED
Bayesian nonparametrics: Dependency and Constraint Modeling
β οΈ Note: TALK via Skype!
Machine Learning @ CUED
Bayesian Nonparametric Model for Power Disaggregation
Machine Learning @ CUED
Frequentist coverage of adaptive nonparametric Bayesian credible sets
Machine Learning @ CUED
Anglican; Particle MCMC inference for Probabilistic Programs
Machine Learning @ CUED
Sparse discriminative latent characteristics for predicting cancer drug sensitivity
Machine Learning @ CUED
Contrastive Learning Using Spectral Methods
Machine Learning @ CUED
Nonparametric Bayesian statistics with exchangeable random structures
Machine Learning @ CUED
Dissecting genotype to phenotype relationships
Machine Learning @ CUED
CANCELLED: Local Deep Kernel Learning for Efficient Non-linear SVM Prediction
β οΈ CANCELLED
Machine Learning @ CUED
Clustering Based on Predictive Variances in Gaussian Process Regression Models
Machine Learning @ CUED
Non-Parametric Conditional Random Fields in Computer Vision and Image Processing
Machine Learning @ CUED
Higher Order Learning for Classification in Emergency Situations
Machine Learning @ CUED
Annealing Between Distributions by Averaging Moments
Machine Learning @ CUED
Applied statistical genetics and next-generation association studies
Machine Learning @ CUED
Applied statistical genetics and next-generation association studies
Machine Learning @ CUED
The combinatorial structure of conditionally i.i.d. negative binomial processes directed by a beta process
Machine Learning @ CUED
Deep Gaussian Processes
Machine Learning @ CUED
Approaches to statistical modeling of network data
Machine Learning @ CUED
Bayesian nonparametric methods for non-exchangeable data
Machine Learning @ CUED
Non-parametric Bayesian Chromatin State Segmentation
Machine Learning @ CUED
Fast Variational Inference in the Conjugate Exponential Family
Machine Learning @ CUED
An application of HDP And IBP for stream-based action recognition and high dimensional data
Machine Learning @ CUED
Using Context and Insight for the Analysis of LittleData?
Machine Learning @ CUED
Feature allocations, probability functions, and paintboxes
Machine Learning @ CUED
Modelling Reciprocating Relationships with Hawkes Processes
Machine Learning @ CUED
Structural Expectation Propagation (SEP): Bayesian structure learning for networks with latent variables
Machine Learning @ CUED
The combinatorial structure underlying a beta processes is that of a continuum of Blackwell-MacQueen urn schemes
Machine Learning @ CUED
Learning of Milky Way Model Parameters Using Matrix-variate Data in a New Gaussian Process-based Method
Machine Learning @ CUED
Identification of causal effects
Machine Learning @ CUED
Probabilistic methods for biomolecular structure simulations
Machine Learning @ CUED
Compressed Sensing Applications in Functional Magnetic Resonance Imaging
Machine Learning @ CUED
Multi-Label Learning with Millions of Categories
Machine Learning @ CUED
Efficient Sampling with Kernel Herding
Machine Learning @ CUED
Frank-Wolfe optimization insights in machine learning
Machine Learning @ CUED
Deep learning for vision: a case study for visual textures, and some thoughts on a general framework
Machine Learning @ CUED
Thermodynamics as a Theory of Decision-Making with Information Processing Costs
Machine Learning @ CUED
Human Behavior Classification with Infinite Hidden Conditional Random Fields
Machine Learning @ CUED
Fast Gaussian process learning for regression, semi-supervised classification, and multiway analysis
Machine Learning @ CUED
Non-parametric Bayesian Learning of User Preferences: Elicitation, Sparsification and Beyond
Machine Learning @ CUED
Structured Prediction using Linear Programming Relaxations
Machine Learning @ CUED
Discovery of Complex Behaviors through Contact-Invariant Optimization
Machine Learning @ CUED
Learning with nonparametric dependence and divergence estimation
Machine Learning @ CUED
Past work and future interests: respectively, the scattering of Anyons and Monte Carlo methods
Machine Learning @ CUED
Non-parametric Bayesian Method and Maximum-A-Posteriori Inference in Statistical Machine Translation
Machine Learning @ CUED
Infinite Structured Explicit Duration Hidden Markov Models
Machine Learning @ CUED
Probabilistic computing: computation as universal stochastic inference, not deterministic calculation
Please see above for contact details for this list.