Computational Statistics, Statistical Methodology, and Machine Learning Research Group. Based at @OxfordStats.
Oxford, England
- Tweets 318
- Following 166
- Followers 3,277
- Likes 255
Pinned Tweet
The OxCSML group @OxfordStats is participating at @NeurIPSConf this
week, with 25 papers in the main program, 3 workshop papers and 1 paper
in dataset track! Do stop by our posters and presentations! Check out csml.stats.ox.ac.uk/news/202… or the following :thread:for further details
1
13
51
We’re happy to announce that 13 papers coauthored by OxCSML group members were accepted at @icmlconf this year. csml.stats.ox.ac.uk/news/201…
1
14
88
We are inviting applications for fully-funded PhD studentships in statistics and machine learning, joint with @OxfordStats @imperialcollege and many industrial partners. statml.io/
2
24
74
Happy to announce that members of the @oxcsml group @OxfordStats will be presenting 19 papers at NeurIPS this year, many in collaboration with a wide variety of other research groups. Good work everyone! Links to arxiv preprints here:
csml.stats.ox.ac.uk/news/201…
1
16
59
We welcome friends, old and new, to Oxford attending the Bayesian Nonparametrics conference! It's an exciting line-up, including keynotes by Aad van der Vaart, Tamara Broderick, and Long Nguyen!
stats.ox.ac.uk/bnp12/
9
55
Hello world! As our first tweet we're happy to announce OxCSML group's participation at #NeurIPS2018: 13 main conf papers co-authored, and workshop invited talks, orgs, and papers.
csml.stats.ox.ac.uk/news/201…
csml.stats.ox.ac.uk/news/201…
18
54
Two out of the 13 @icmlconf papers from the OxCSML group got Honourable Mentions for Best Papers! Congratulations to @adam_golinski Zhu Li @jeanfrancois287 @tom_rainforth @sejDino and collaborators @frankdonaldwood @DinoOglic !
csml.stats.ox.ac.uk/news/201…
csml.stats.ox.ac.uk/news/201…
8
44
The OxCSML group @OxfordStats is participating at @icmlconf this week, with 13 papers in the main conference and a Test of Time Award @yeewhye!
Do stop by our posters and presentations!
csml.stats.ox.ac.uk/news/202…
Check out the following 🧵 for further details ⬇️
4
20
42
Congratulations to @jovana_mitr for passing her viva titled ‘representation learning with kernel methods, applications in likelihood-free inference, causal discovery and neural networks’.@sejDino @yeewhye
31
Join us for our OxCSML seminar on May 7th, at 3:30 pm (UK time). Aki Vehtari @avehtari (Aalto University) will be speaking about Practical pre-asymptotic diagnostic of Monte Carlo estimates in Bayesian inference and machine learning.
eventbrite.co.uk/e/oxcsml-se…
3
8
30
Join us for the next OxCSML seminar today by @victorveitch on Causal Estimation with Machine Learning without (Simple) Unconfoundedness! UK time 330pm.
github.com/oxcsml/ML_bazaar/…
zoom.us/j/91534051601?pwd=Zl…
5
25
We have just collated recent ML conference publications from our group here csml.stats.ox.ac.uk/news/: 2 @iclr_conf, 2 UAI, 5 @Aistats2020 and 8 @icmlconf papers! Congrats everyone!
5
23
Join us this Friday Feb 26th at 3.30pm GMT for our OxCSML seminar by
Karolina Dziugaite
(Element AI)
who will talk about Distribution-dependent generalization bounds for noisy, iterative learning algorithms
Zoom details available following registration
eventbrite.co.uk/e/oxcsml-se…
1
4
23
Join us this Friday at 3.30pm BST for our next OxCSML seminar!
We're very pleased to welcome @JulyanArbel, who will be speaking on 'Approximate Bayesian computation with surrogate posteriors'.
Zoom details available upon registration:
eventbrite.co.uk/e/oxcsml-se…
7
21
Congratulations to @RousseauJudith for being awarded an @ERC_Research advanced grant on General theory for Big Bayes! #ERCAdG stats.ox.ac.uk/archive-news/… erc.europa.eu/news/erc-2018-…
1
19
Join us this Friday 26th March at 3:30pm GMT for our next seminar!
Benjamin Guedj @bguedj
will be talking about ``A primer on PAC-Bayesian learning *followed by* News from the PAC-Bayes frontline''
Zoom details available following registration:
eventbrite.ca/e/148031439019
3
19
We are delighted to announce creation of an @ELLISforEurope unit at Oxford spanning @oxengsci @CompSciOxford @OxfordStats . OxCSML faculty Chris Holmes and @yeewhye are also helping co-direct the Robust ML programme in ELLIS.
New ELLIS unit brings together #AI experts from @oxengsci @CompSciOxford @OxfordStats, to shape how machine learning and artificial intelligence will change the world. eng.ox.ac.uk/news/new-oxford…
4
18
Come work with the amazing @RousseauJudith and the OxCSML group!
📢JOB VACANCY: Postdoctoral Research Assistant for the ERC project General Theory for Big Bayes, reporting to Professor Judith Rousseau.
📆Deadline for applications noon on 12 March. my.corehr.com/pls/uoxrecruit…
7
14
Join us this Friday at 3.30pm GMT for our next OxCSML seminar by
Veronika Rockova (UChicago)
who will be talking about 'METROPOLIS-HASTINGS VIA CLASSIFICATION'!
Zoom details available following registration at eventbrite.ca/e/oxcsml-semin…
6
13
Join us tomorrow at 3.30pm GMT for our next OxCSML seminar by @sineadwilliamso who will be talking about 'Bayesian nonparametric models for interaction networks'!
Zoom details available following registration at eventbrite.co.uk/e/oxcsml-se… .
2
13
Bayesian Learning via Stochastic Gradient Langevin Dynamics
@wellingmax @yeewhye
Time of Time Award
Thursday 8pm (PDT), Friday 4am (BST) icml.cc/virtual/2021/test-of…
1
13
Tomorrow @chrisgamble88 from @DeepMind will give an OxCSML seminar on AI as a Science and AI for Science. Jan 21, 11am, on Zoom zoom.us/j/97762995154?pwd=az…
github.com/oxcsml/ML_bazaar/…
1
6
11
Nice work by our Florence Nightingale fellow @mena_gonzalo !
An analysis of #COVID19 incidence and mortality in Santiago, Chile, highlights major consequences of healthcare disparities in a highly segregated city, showing that these inequalities disproportionately affected younger people @OxfordStats @HarvardChanSPH fcld.ly/qjpbyfd
3
12
🤖 Outcome-Driven Reinforcement Learning via Variational Inference 🤖
🎙️Talk: neurips.cc/virtual/2021/post…
📄Paper: openreview.net/forum?id=4bza…
🖥️Results: sites.google.com/view/od-ac
@timrudner @vitchyr @rowantmc @yaringal @svlevine
1
1
12
Join us this Friday Feb 19th at 3.30pm GMT for our next OxCSML seminar by
Francois-Xavier Briol @fx_briol (UCL)
who will be talking about 'Kernel-based robust inference for intractable likelihood models'
Zoom details available following registration at
eventbrite.co.uk/e/oxcsml-se…
7
13
Delighted that our paper Towards A Unified Analysis of Random Fourier Features arxiv.org/abs/1806.09178 received an honorable mention at #ICML2019. Great work by Zhu Li, @jeanfrancois287 and @DinoOglic. Check out @DinoOglic's talk at 2pm today icml.cc/Conferences/2019/Sch…
13
Spotlight this morning at 1025 room 220e
I'm excited to finally release source code for SQAIR (which was accepted as a spotlight at NIPS this year):
github.com/akosiorek/sqair
Thanks @hyunjik11, @IngmarPosner and @yeewhye for help with this!
13
Deep Adaptive Design (DAD) enables fast, adaptive experimentation. Learning a design policy net, DAD removes need for costly computations at each step of the experiment and makes decisions in <1sec using a single forward pass.
@AdamEFoster @desirivanova Ilyas Malik @tom_rainforth
1
2
10
Join us this Friday for our next OxCSML seminar!
@RogerGrosse will be talking about ``Self-tuning networks: Amortizing the hypergradient computation for hyperparameter optimization''!
Zoom details available following registration:
eventbrite.ca/e/oxcsml-semin…
3
10
Delight to announce that our #icml2019 paper Amortized Monte Carlo Integration (see below) has been awarded an honourable mention for best paper! Don't miss @adam_golinski's talk at 11.40am in room 101.
11
Thanks for coming and giving a nice talk @OxfordStats!
10
This friday 3:30 pm (London time) we have the great Caroline Uhler (MIT) in our OxCSML seminar, who will be speaking about Causality and Autoencoders in the Light of Drug Repurposing for COVID-19. You are all invited!
eventbrite.co.uk/e/oxcsml-se…
3
10
Join us this Friday 12th March at 3:30pm GMT for our next seminar!
@MuratAErdogdu will be talking about `` Convergence of Online SGD under Infinite Noise Variance, and Non-convexity''
Zoom details available following registration:
eventbrite.ca/e/oxcsml-semin…
4
9
Continuous Hierarchical Representations with Poincaré Variational Auto-Encoders (poster Tue Dec 10th) by @MathieuEmile @charlinelelan @cjmaddison, Ryota Tomioka (MSR Cambridge), @yeewhye
1
8
@NeurIPSConf meet-up @OxfordStats @oxengsci this week :) we are streaming events from neurips and there is local unconference and talks. Join us! Thanks to organisers @ShehZaidi @bobby_he, sponsors @graphcoreai @_FiveAI ! sites.google.com/view/oxford… @le_roux_nicolas
3
6
11
Congrats!
9
Equivariant Learning of Stochastic Fields: Gaussian Processes and Steerable Conditional Neural Processes
We study vector valued stochastic processes with Euclidean symmetris, and apply the results to Guassian and Neural processes. @PHolderrieth, @MHutchinson141 @yeewhye
1
2
9
Datasets&Benchmarks Track:
🤖Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks🤖
📄Paper: openreview.net/forum?id=jyd4…
🖥️Code: github.com/google/uncertaint…
@neilbband @timrudner @qixuan_feng @filangelos @zacharynado @dusenberrymw @Ghassen_ML @dustinvtran @yaringal
1
5
9
🤖 Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning 🤖
📄Paper: arxiv.org/abs/2106.04015
📡Blog: ai.googleblog.com/2021/10/ba…
🖥️Code: github.com/google/uncertaint…
@zacharynado @neilbband @timrudner @sirbayes @balajiln @yaringal @dustinvtran
1
5
8
Congrats!
1
8
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise (poster Wed Dec 11th) by Thanh Huy Nguyen, @umutsimsekli, Mert Gurbuzbalaban and Gaël Richard at @ParisTech_News and Rutgers.
2
7
Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model (poster Tue Dec 10th) by @atilimgunes @BayesianBrad @KyleCranmer @frankdonaldwood and others from @OxfordTVG, @intel, @UBC @BerkeleyLab @nyuniversity.
1
4
8
Spotlight in AutoML: Wed 21 Jul 02:00 BST — 03:00 BST (Tues 6 p.m. PDT) icml.cc/virtual/2021/poster/…
Poster Session 2: Wed 21 Jul 04:00 BST — 07:00 BST (Tues 8 p.m - 11 p.m. PDT)
@wanxingchen_, @nguyentienvu, Huong Ha, Binxin Ru, @cong_ml @maosbot
arxiv.org/abs/2102.07188
1
3
7
Asymmetric Heavy Tails and Implicit Bias in Gaussian Noise Injections
Injecting Gaussian noise = bias in SGD because of heavy-tailed asymmetric noise on gradients.
@CamutoDante · Xiaoyu Wang · Lingjiong Zhu · @cholmesuk · Mert Gurbuzbalaban · @umutsimsekli
1
2
6
BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning (poster Thu Dec 12th) by @BlackHC @joost_v_amersf @yaringal with @OATML_Oxford @CompSciOxford
1
1
7
Fractal Structure and Generalization Properties of Stochastic Optimization Algorithms:
We link the generalization error to the 'complexity' of the fractal structure created during training.
With @CamutoDante @GeorgeDeligian9 @MuratAErdogdu @MGurbuzbalaban @umutsimsekli L. Zhu
1
4
6
Join us this Friday for our next OxCSML seminar!
We're very pleased to welcome @JamesJohndrow who will be talking about ``Spectral gaps and error estimates for infinite-dimensional Metropolis-Hastings with non-Gaussian priors''
Register for zoom link:
eventbrite.ca/e/oxcsml-semin…
1
7
Also, don’t miss out on the invited talk A Bayesian Perspective on
Neural Processes by Yee Whye Teh @yeewhye at Bayesian Deep Learning
Workshop on Dec 14! neurips.cc/Conferences/2021/…
1
1
7
🤖 On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations 🤖
🎙️Talk: neurips.cc/virtual/2021/post…
📄Paper: openreview.net/forum?id=sS8r…
🖥️Results: sites.google.com/view/nppac
@timrudner @cong_ml @maosbot @yaringal @yeewhye
1
3
6
#supportingELLIS to support European excellence in machine learning and AI.
We are joining forces in #SupportingEllis: The European Laboratory for Learning and Intelligent Systems (ELLIS) announced the formation of its professional association at #NeurIPS : is.mpg.de/en/news/european-l… @bschoelkopf We have prominent support from the world´s top #AI companies!
4
6
Join us this Friday May 14th for our OxCSML seminar. This time we have Cynthia Rudin (Duke) with "Do Simpler Models Exist and How Can We Find Them?" @CynthiaRudin
eventbrite.co.uk/e/cynthia-r…
1
7
VIREL: A Variational Inference Framework for Reinforcement Learning (Spotlight Wed Dec 11th 10:25 -- 10:30 AM @ West Exhibition Hall B) by Matthew Fellows, Anuj Mahajan, @timrudner, @shimon8282 with @whi_rl @CompSciOxford.
1
6
Come join awesome bunch of folks working at the interface of statistics and machine learning.
StatML CDT Admissions 21/22
The deadline for the 1st round - FRIDAY 13 NOVEMBER is approaching fast (only unlucky for some!!). Go to our website statml.io for information on how to apply. We look forward to receiving your application.
4
7
Thank you @suchisaria for a great visit and an inspiring distinguished seminar at @OxfordStats today!
Really enjoyed today's talk by @suchisaria on her work on developing ML approaches for medical diagnostics.
6
Congratulations @desirivanova . Well done!
Congratulations to @desirivanova 🥉 (@OxUniMaths), Matthew Tointon 🥇 (@BristolUniMaths) and Teresa Bautista 🥈 (@KingsCollegeLon) on their @STEM4Brit awards this afternoon! 👏🎉🧮 #mathematics #stem @UKParliament
6
Generalized Sliced Wasserstein Distances (poster Tue Dec 10th) by Soheil Kolouri, Kimia Nadjahi, @umutsimsekli, Roland Badeau, Gustavo Rohde at @ParisTech_News HRL Laboratories LLC and U Virginia
1
3
5
Congrats @EmiliaPompe, wonderful work!
Wonderful surprise: my work done at @OxfordStats on Posterior Bootstrap received the #isba2021 Best Student/Postdoc Contributed Paper Award. Thank you @ISBA_events and everyone who was supporting me with this project!
#WomenInSTEM
1
5
Join us this Friday 5th March at 11am GMT for our next seminar! Linda Tan (National University of Singapore) will be speaking about the 'Use of model reparametrization to improve variational Bayes'.
Zoom details available following registration:
eventbrite.co.uk/e/oxcsml-se…
2
6
LieTransformer: Equivariant Self-Attention for Lie Groups
We propose a self-attention-based architecture that is equivariant to arbitrary Lie groups and their discrete sub-groups.
@MHutchinson141 @charlinelelan @ShehZaidi @emidup @yeewhye @hyunjik11
arxiv.org/abs/2012.10885
1
1
6
On the Fairness of Disentangled Representations (poster Thu Dec 12th) by @FrancescoLocat8, Gabriele Abbati, @tom_rainforth, Stefan Bauer, @bschoelkopf @OlivierBachem with @MPI_IS @GoogleAI
1
2
5
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning:
@janundnik @neilbband* @clarelyle, @AidanNGomez, @tom_rainforth, @yaringal, @OATML_Oxford
🚀 Non-Parametric Transformers 🚀
papers.nips.cc/paper/2021/ha…
1
2
5
Oops. 14 papers!
On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Process
We show that importance-weighted VI for deep GPs can lead to arbitrarily poor gradient estimates and how to prevent this from happening
@timrudner @yaringal @tom_rainforth
1
1
5
We also have three workshop papers:
🤖 PCA Subspaces Are Not Always Optimal for Bayesian Learning 🤖
📄Paper: openreview.net/forum?id=iPYH…
🎙️Talk: nips.cc/Conferences/2021/Sch…
Alexandre Bense @amirjoudaki @timrudner @vincefort
1
3
4
🏃♀️🧪Active Testing: Sample-Efficient Model Evaluation
Active learning is label-efficient only in training. Active testing introduces strategies for sample-efficient evaluation.
🗣 ICML Poster Session 5
✍️ @janundnik @sebfar @yaringal @tom_rainforth
📄 arxiv.org/abs/2103.05331
1
1
4
Two short term departmental lectureships in @OxfordStats : stats.ox.ac.uk/vacancies/
3
5
Join us this Friday (June 25th) for our next OxCSML seminar!
We're very pleased to welcome
Quan Zhou (Texas A&M University)
who will be talking about ``Complexity of local MCMC methods for high-dimensional model selection''
Register for zoom link: eventbrite.ca/e/oxcsml-semin…
5
Differentiable Particle Filtering
Leveraging regularized Optimal Transport for resampling enables end-to-end Differentiable Particle Filtering, with @AdrienCorenflos, @JamesTThorn, @GeorgeDeligian9, @ArnaudDoucet1
Paper: arxiv.org/abs/2102.07850
Code: github.com/JTT94/filterflow
1
4
Long presentation in Probabilistic Methods 1: Wed 21 Jul 1300 BST 0500 PDT icml.cc/virtual/2021/poster/…
Poster Session 3: Wed 21 Jul 1600 BST 0800 PDT
arxiv.org/abs/2102.11086
@YangjunR @karen_ullrich @_dsevero
James Townsend, Ashish Khisti, @ArnaudDoucet1 Alireza Makhzani @cjmaddison
2
1
4
Spotlight presentation in Reinforcement Learning 5, Wed 21 Jul 02:00 BST — 03:00 BST (Tues 6 p.m. PDT) icml.cc/virtual/2021/poster/…
Poster Session 2: Wed 21 Jul 04:00 BST — 07:00 BST (Tues 8 p.m - 11 p.m. PDT)
@philipjohnball, @cong_ml, @jparkerholder, Stephen Roberts #ICML2021
1
1
4
Variational Bayesian Optimal Experimental Design (spotlight Tue Dec 10th 04:40 -- 04:45 PM @ West Ballroom C) by Adam Foster, Martin Jankowiak, Elias Bingham, Paul Horsfall, @yeewhye @tom_rainforth, Noah Goodman. Work done by Adam during his internship at @UberAILabs.
1
4
Hamiltonian Descent for Composite Objectives (poster Wed Dec 11th) by Brendan O’Donoghue and @cjmaddison at @DeepMindAI
1
4
Spotlight in Multi-task Learning 1: Fri 23 Jul 01:00 — 02:00 BST (Thu 5 p.m. PDT) icml.cc/virtual/2021/poster/…
Poster Session 6: Fri 23 Jul 05:00 — 08:00 BST (Thu 9 p.m. - midnight PDT)
@luisa_zintgraf, @lylbfeng, @cong_ml, @MaxiIgl, @kristianhartika, @katjahofmann, @shimon8282
1
4
Deconditional Downscaling with Gaussian processes
We frame downscaling of indirectly matched spatial fields as an inverse conditional expectation problem and propose novel probabilistic solution based on Gaussian processes and kernel mean embeddings @Chau9991 @shbouabid @sejDino
1
2
4
BayesIMP: Uncertainty Quantification for Causal Data Fusion
We propose a Bayesian Conditional Mean Embedding to embed the interventional distribution in the RKHS to estimate the average treatment effect with uncertainty quantification under the causal data fusion setting.
1
3
4
Congrats!
I’ve been very fortunate throughout my career to work with many fantastic scientists and wonderful people, but even amongst that the team @Genomicsplc are amazing. I love every minute of it! Thanks!!
1
3
Provably Strict Generalisation Benefit for Equivariant Models
The first strictly non-zero improvement in generalisation for equivariant models.
@BrynElesedy @ShehZaidi
Poster session 1, Spot C6!
link: bit.ly/3ee9W5W
1
3
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
A simple self-supervised context adaptation algorithm which allows generalisation to novel environments from offline data on a single environment.
arxiv.org/abs/2104.05632
1
3
Congrats @TheFrappies !
Following the Italian successes at the Olympics (I might take this a bit too further, I know), I'll go for a self-congratulatory tweet. I won one of the Best Student/Postdoc Contributed Paper Award at @ISBA_events! Thanks, this was unexpected (I actually thought it was a scam)!
2
See how your local authority is doing with suppressing Covid-19.
localcovid.info
With folks @oxcsml and Royal Society DELVE Initiative, we've been working on a model and website for tracking Covid-19 in British local authorities. Check out
localcovid.info
With lockdown lifted and Christmas in sight, we hope this will be useful for everyone in GB!
3
Uncertainty Quantification in End-to-End Implicit Neural Representations for Medical Imaging
Francisca Vasconcelos, @bobby_he, @yeewhye
Oral at MedNeurIPS: neurips.cc/virtual/2021/work…
Poster at Bayesian Deep Learning Workshop: neurips.cc/virtual/2021/work…
Paper: cse.cuhk.edu.hk/~qdou/public…
1
2
3
Spotlight presentation in Gaussian Processes 1: Thu 22 Jul 13:00 — 14:00 BST (5 a.m. - 6 a.m. PDT)
Poster Session 5: 17:00 - 19:00 BST (9 a.m. - 11 a.m. PDT) icml.cc/virtual/2021/poster/…
🎙️Talk: icml.cc/virtual/2021/poster/…
📄Paper: arxiv.org/abs/2011.00515
🖥️Code: github.com/timrudner/snr_iss…
2
3
Probabilistic Programs with Stochastic Conditioning @dtolpin, @yuaanzhou, @Tom, @hyang144 We formalize and show how to condition programs on variables taking a particular distribution, rather than a fixed value proceedings.mlr.press/v139/t… #ICML2021
1
3
Diffusion Schrödinger Bridge with Applications to Score-Based Generative Modeling (spotlight)
A principled generalization of score/diffusion based generative modeling using iterative reverse diffusions, with connections to optimal transport.
1
3
Congrats Alison!
Oxford Statistician & Mathematician Alison Etheridge has been appointed Chair of the Council for the Mathematical Sciences, the organisation that represents the wide breadth of the mathematical sciences in the UK. @OxUniMaths
cms.ac.uk/wp/news-and-press-…
1
3
Further info:
Poster session 1: neurips.cc/virtual/2021/sess…
Paper: arxiv.org/abs/2105.12909
Code: github.com/shahineb/decondit…
1
3
Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance (poster Thu Dec 12th) by Kimia Nadjahi, Alain Durmus, @umutsimsekli and Roland Badeau at @ParisTech_News and @ENS_ParisSaclay.
1
1
2
Online Variational Filtering and Parameter Learning:
We exploit forward Bellman recursions and RL ideas for the ELBO in state-space models. With @AndrewC_ML @YuyangShi0 @tom_rainforth @ArnaudDoucet1
Oral session 1: neurips.cc/virtual/2021/sess…
Paper: arxiv.org/abs/2110.13549
1
3
On Locality of Local Explanation Models:
We investigate why popular model-agnostic local explanation models like SHAP are not locally faithful and how their locality can be increased with neighbourhood sampling. With @SGhalebikesabi, @TerLucile,@karlado,@cholmesuk
1
3
These are great early career fellowships!
📢Three exciting jobs! Florence Nightingale Bicentennial Fellow in Statistics, Probability or a related subject (x2) and Glasstone Research Fellowship in Science, both for researchers at an early stage of their career. More details: stats.ox.ac.uk/vacancies/
1
3
Distributed Machine Learning with Sparse Heterogeneous Data
Dominic Richards, Sahand N. Negahban, Patrick Rebeschini
Poster Session 6 : neurips.cc/Conferences/2021/…
arXiv paper: arxiv.org/abs/1912.01417
1
2
Paper info:
This preliminary work presents the first large-scale study of implicit neural representations with uncertainty quantification. Well-calibrated, accurate image reconstruction algorithms can improve doctor diagnoses and reduce patient radiation exposure.
1
The benefit is given in terms of properties of the group and the RKHS, and arises from an orthogonal decomposition of the RKHS into invariant and non-invariant components.
Poster session 2.
Paper: arxiv.org/abs/2106.02346
1
2
Provably Strict Generalisation Benefit for Invariance in Kernel Methods:
@BrynElesedy
We show that, when correctly specified, invariance improves generalisation in kernel ridge regression.
1
2