Something new: soon · decision-making, machine learning, artificial intelligence · anti-ideological · Assistant Research Professor @Cornell, prev @CambridgeMLG
Soon-to-be in San Francisco
- Tweets 3,658
- Following 1,635
- Followers 8,338
- Likes 5
Pinned Tweet
Today's conventional wisdom often says agentic coding works best for slop - think 500k lines of Python.
Let me challenge that: in two days, I built the code equivalent of fragile glass - a concurrent hash table in CUDA. And it's faster than Nvidia's!
New blog post - link below!
3
2
20
4,318
As a rule, I don’t dismiss other people’s research areas.
People know all kinds of things I don’t, including technical reasons why an unpopular method might one day achieve performance no other method can.
Consequently, I ask others not to dismiss mine.
Let’s talk about why.
55
105
1,855
513,223
I'm an academic, I left the UK, and I brought a loved one with me to the US.
After ten months here, I'm convinced the intellectual environment and resources here are decisively better than at the best places in the UK.
If you're serious about science, come to the US!
25
95
1,249
437,699
Announcing: Geometric Kernels, a library for computing kernels on non-Euclidean spaces like graphs and manifolds!
Now, it's much easier to try out some of the geometric Gaussian process models we've been developing - just install a Python package!
geometric-kernels.github.io
11
170
921
I'm going to try an experiment, and open-source my PhD dissertation writing by making the thesis document visible to the public while I write it.
Check it out and follow along!
github.com/aterenin/phdthesi…
13
56
564
My PhD thesis "Gaussian Processes and Statistical Decision-making in Non-Euclidean Spaces" is now on arXiv!
Check it out!
arxiv.org/abs/2202.10613
11
58
521
Got my first internship rejection of the application season, by DeepMind. Always wanted to see whether working at an industry research lab would be for me, and this is my last chance before graduating to find out. Is anyone looking for a machine learning research intern?
38
47
439
Ever wanted a Gaussian process whose domain is a manifold important enough to actually have a name?
If it's a Lie group or homogeneous space, we've worked out a general recipe for computing sq. exp. (heat, diffusion, ..) and Matérn kernels on it!
arxiv.org/abs/2208.14960
13
63
439
Yesterday, I submitted my PhD thesis!
My experiment in writing in an open-source format was a resounding success! I want to thank everyone who liked, commented, or gave me feedback or encouragement - you made the process so much more fun and exciting!
github.com/aterenin/phdthesi…
14
32
422
Our two-part foundational series of papers on stationary kernels and Gaussian processes on Lie groups and homogeneous spaces is accepted at JMLR!
If you want to know the geometric roots of various phenomena in kernels and Fourier features - with pretty pictures - check it out!
5
37
407
31,901
We’re extremely excited to announce the NeurIPS Workshop on Bayesian Decision-making and Uncertainty: from probabilistic and spatiotemporal modeling to sequential experiment design!
This will take place at NeurIPS 2024, in Vancouver, BC, Canada, either on December 14th or 15th.
1
64
380
39,717
Belated career announcement: I've joined Cornell as an Assistant Research Professor!
This is a 3-year fancy research fellowship (non-tenure-track), during which I'm looking to shift my research to decision-making systems like Bayesian optimization, bandits, and online learning.
13
3
385
46,349
Some news: I've accepted an offer to join the Machine Learning Group within Computational and Biological Learning at the University of Cambridge as a postdoc.
Excited to be part of a research group that I have long respected for its astonishing quality of ideas!
@CambridgeMLG
20
5
371
So let’s learn from the scientific mistakes of the past, and not broadly dismiss *any* area of machine learning.
Better to lose a tiny bit of taxpayer money but give scientists room to experiment.
Else, valuable ideas might go undiscovered because everyone thinks the same way.
8
11
328
54,860
The NeurIPS high school track has made its way to Chinese social media.
The collaborator who sent me this said there is at least one example of a professor asking their PhD student to help write a paper for one of their kids so that it can help their college admissions abroad.
13
42
331
71,031
A slightly-contrarian opinion: since AlphaGo, it has been obvious to essentially everyone that combining learning / pre-training with some form of search / inference-time compute is the right path to AI.
What has not been obvious is how - the technical details to make it work.
8
23
331
43,480
I started working on machine learning in my mid-twenties, after simultaneous degrees in psychology and statistics - the latter with no linear algebra, no optimization, no decision theory, no rigorous proofs, and virtually no code.
I didn't even know what gradient descent was.
Am I too late to get into deep-tech / hardware / physics / science / engineering?
I didn't start my engineering degree until I was 24. Before that I was working in marketing and sales, I had a humanities degree, and for my entire life had been "not a math guy"
So no. Go do it
10
9
294
67,631
Efficiently sampling functions from Gaussian process posteriors
Time to showcase our ICML paper! Here, we develop techniques for linear-time sampling from GP posteriors, which also enables one to easily differentiate through GP sample paths.
avt.im/publications/2020/07/…
(1/n)
ALT https://avt.im/publications/2020/07/09/GP-sampling
3
59
324
Open-source PhD thesis update!
Yesterday and today, I wrote a draft introduction for my thesis, which introduces Bayesian learning, statistical decision-making, and Gaussian processes at a broad, informal level, motivating why these concepts should be formalized.
Check it out!
7
28
310
Graph neural networks are one of the best-kept secrets of the deep learning revolution: a model class that both really works, to the point of creating actual commercial value, and gives a useful conceptual framework for thinking about deep learning.
Our team partnered with @googlemaps to boost the accuracy of ETA estimation in major cities across the world by up to 50% using graph neural networks. Today we’re pleased to share the full paper, which has also been recently accepted @CIKM2021. Paper: dpmd.ai/maps 1/
2
43
308
You've seen many descriptions of Bayes' Rule. But have you ever seen one that's this pretty? 😄
6
45
289
Ever wanted a Gaussian process whose domain is a manifold important enough to have a name?
We've worked out a general recipe for building kernels on non-compact manifolds which are symmetric spaces, incl. hyperbolic space and the space of SPD matrices!
arxiv.org/abs/2301.13088
7
42
277
47,195
Wow, over 500 people decided my open-source PhD thesis writing idea was cool enough to give it a like! Thank you all for the encouragement!
Today, I finished the section on multivariate Gaussians - introducing and reviewing their properties. Check it out!
7
10
255
Time to showcase our group's final AISTATS paper, "Learning Contact Dynamics using Physically Structured Neural Networks" which explores modeling of non-smooth contact dynamics.
Shoutout to first author Andreas Hochlehnert - this is his MSc work!
avt.im/publications/2021/01/…
@mpd37
5
41
252
The people developing Bayesian learning are not stupid.
There are things it can do other (general) methods can’t, my chief example - of commercial and scientific importance - being Bayesian optimization and other decision-theoretic problems where we want to minimize regret.
3
4
231
27,429
Announcing the 2022 NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems!
Please consider submitting a 4-page extended abstract by September 22nd!
gp-seminar-series.github.io/…
Thanks to amazing organizers @gpleiss, @liza_p_semenova, @ziwphd
ALT NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems
1
43
237
Passed my PhD viva with minor corrections!
Thanks very much to the committee for examining me, and my advisors and collaborators for the support over the years!
@StefanoErmon @mmbronstein @mpd37 @flaxter
17
1
236
So what does our friend Valeriy, from the original tweet, want us to do?
Go big on what is popular *today*, chiefly (I presume deep net based) conformal prediction.
Other approaches are a “waste of taxpayer money”.
People said the same thing about neural nets a decade ago.
1
5
217
28,968
It’s easy to jump on the right bandwagon with the benefit of hindsight.
What matters is how you act towards ideas that may not be quite there yet.
Do you dismiss areas broadly, or do you get into nuanced technical discussion?
2
12
217
25,874
At the NeurIPS optimization workshop. In my opinion, the “most creative poster design” award should go to these folks:
3
13
205
19,030
A preview of a figure from a paper landing on arXiv very soon!
Can't wait to tell you what I've been thinking about for the past year!
Stay tuned..
8
6
204
28,276
First: make no mistake - if you insult students I’ve worked with - complete with surface-level “Darwin College” jokes - you insult me.
Still, instead of dwelling on this, let’s focus on the way of thinking that leads one here.
We can learn something important from it.
4
1
186
35,428
Announcing the virtual seminar series on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems!
Time: Mondays at 16:00 UTC
The inaugural keynote will be given by @ta_broderick on March 14th (pi day). Please register on the website!
gp-seminar-series.github.io
3
42
190
Valeriy’s point is that Bayesian methods, Gaussian processes included, can give poorly calibrated results.
Therefore: developing them is a waste of resources and should not be pursued.
This point can be made without “Darwin”
Worse: this kind of thinking harms the ML ecosystem.
4
2
188
36,305
New preprint!
This is a hardcore technical paper on Thompson sampling - as a strategy for the so-called online learning game.
I think it's one of the most long-term important things I have ever worked on due to what it makes possible.
But that needs explaining - thread below!
6
21
200
28,657
If you are interested in AI research, and good at mathematics, but discouraged by advice to focus on code, ignore it.
On some problems, progress will come from experiments and empirical work. On others, it will come from theorem and proof.
The field needs both kinds of people.
This is probably well-known in some circles but not everywhere.
The most important skill for Research Scientists in AI (at least at @OpenAI) is software engineering.
Background in ML research is sometimes useful, but you can usually get away with a few landmark paper.
8
12
192
So let’s talk about it!
First: imagine you’re Yann LeCun in the 90s. You’ve seen what neural nets can do on tiny problems by today’s standards. You’re convinced, if only there was more data and compute, they’d decisively solve various hard image processing problems.
3
2
182
33,364
So what happens? Neural nets develop slowly, until ImageNet - at that point, the results became so strong anyone ignoring them was a fool.
And there are plenty of folks who - still today - dismiss deep learning as some kind of non-rigorous mumbo-jumbo going away soon.
1
1
179
28,436
Today at ICLR, we're presenting "Stochastic Gradient Descent for Gaussian Processes Done Right".
This work uses insights from optimization theory to improve performance of stochastic-gradient-descent based large-scale Gaussian processes training algorithms.
More below:
2
17
183
45,018
You try to convince your colleagues neural nets are promising. You get strong empirical results for the time and show them to others.
And how do people react? Skepticism.
“You can’t prove SGD converges, therefore it doesn’t”
“We need more SVMs (& other ideas big at the time)”
3
2
173
31,488
Got rejected for a junior research fellowship at Cambridge, after making it to the final interview round. While I’m disappointed to still be on the academic job market into next year, I’m incredibly honored to have made it to the end in a contest with <1% success rate.
6
2
173
I recently wrote a blog post on what successful research might look like for me, in order to better orient my work at Cornell over the next several years.
I'd love your thoughts on it!
avt.im/blog/on-successful-re…
2
21
178
24,033
Variational Integrator Networks for Physically Structured Embeddings
Time to showcase our AISTATS paper! We use ideas from neural ODEs to study data-efficient representation learning of physical dynamical systems.
avt.im/publications/2020/03/…
arxiv.org/abs/1910.09349
(1/n)
7
38
176
Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent
New preprint - with some exciting and counterintuitive results - is now on arXiv!
Joint work with: @JihaoAndreasLin @JaviAC7 @shreyaspadhy David Janz @jmhernandez233
arxiv.org/abs/2306.11589
2
28
167
22,455
When working with a Gaussian process, have you ever wondered why Cholesky factorization failed, or a CG solve did not converge?
Answer: it's because you've got redundant, overlapping data points.
And that's just the starting point! On arXiv now!
arxiv.org/abs/2210.07893
2
14
150
Next Monday at UAI 2024, together with @vabor112, we'll give a tutorial on Geometric Probabilistic Models!
The key theme will be on principled geometry-aware handling of uncertainty.
We're really excited to present, and will be making our slides and notebooks available online.
1
13
145
10,647
I haven't yet tweeted about Chapter 3 of my thesis - time to tell you about that!
This chapter studies properties of geometric Gaussian process models, such as the Matérn class.
Here's what the covariance kernel of these processes looks like on a sphere and dragon manifold!
3
9
141
Very honored and excited to announce that our work "Efficiently sampling functions from Gaussian process posteriors" received an honorable mention for the ICML2020 outstanding paper award! (1/n)
Efficiently sampling functions from Gaussian process posteriors
Time to showcase our ICML paper! Here, we develop techniques for linear-time sampling from GP posteriors, which also enables one to easily differentiate through GP sample paths.
avt.im/publications/2020/07/…
(1/n)
ALT https://avt.im/publications/2020/07/09/GP-sampling
1
15
139
There's no talk tomorrow for the Gaussian process seminar series due to the holiday, but check out the schedule for more upcoming seminars!
gp-seminar-series.github.io
12
143
Announcement: with my Cambridge funding ending soon, I'm looking for postdoc opportunities in the United States or Canada!
I'm interested in branching out from Gaussian processes and working on robotics-inspired ML such as planning, RL, and world models.
Please reach out!
3
20
130
41,151
My first submittable faculty application draft is done, so perhaps it's time to announce: I'm on the machine learning and computer science faculty job market!
I study data-efficient learning and decision-making. If you want to know more, please reach out, and spread the word!
6
21
135
Today, I graduated from Imperial College.
Reflecting, what a journey it’s been - plenty of challenges along the way.
Since I started, all I’ve wanted was to calmly and peacefully work on and solve the problems that interested me.
I still haven’t gotten there. But I made it!
6
128
Here's a teaser from a paper I've been working on this year - it's a squared exponential Gaussian process on a real projective space! And there's so much more..
Landing on arXiv hopefully in a few days!
3
5
124
Announcement: the submission deadline for the NeurIPS Workshop on Bayesian Decision-making and Uncertainty has been extended!
The new deadline is September 5, 2024, anywhere on earth.
Looking forward to your submissions!
1
17
122
13,892
Even more good news! Our paper "Pathwise Conditioning of Gaussian Processes" is accepted at the Journal of Machine Learning Research! This work explores some ideas following our ICML paper - blog post for that one below!
@mpd37
arxiv.org/abs/2011.04026
avt.im/publications/2020/07/…
2
16
125
Academic career milestone: for the first time, somebody who I've never met or communicated with online, and who hasn't previously worked with one of my advisors, invited me to give a talk.
2
1
120
Matérn Gaussian processes on Riemannian manifolds
Time to showcase our latest work! Here, we develop training techniques for Matérn Gaussian processes f : M -> R on Riemannian domains, including computing the kernels of said processes. (1/n)
avt.im/publications/2020/06/…
3
18
109
After a year or two of not submitting anything to machine learning conferences, my NeurIPS record this year is three for three!
I'll tweet about the papers - and about the new job I just started - soon, but for now I'm just happy that my work is finally ready to share with you!
5
113
23,673
We've updated the schedule for the NeurIPS Workshop for Bayesian Decision-making and Uncertainty - it now includes all the talk titles!
Check it out! Looking forward to seeing everyone on Saturday!
2
12
114
9,318
“Physics isn’t mathematics, where major advances can be done with a pen and piece of paper. It’s an experimental science..”
To dismiss mathematics is to dismiss reasoning itself. Doing so risks repeating the same class of mistakes that held neural networks back for years..
Machine learning isn’t mathematics or physics, where major advances can be done with a pen and a piece of paper. It’s an engineering science - @fchollet
6
13
107
This approach never worked for me, not even when I was looking for postdocs.
I don’t think it was my emails: they were shorter, content-dense, and clearly spelled out what I can do for the recipient.
I was a lot more successful in meeting people, then contacting those I knew.
Cold emails are hard and good ones can change a life. Here is my email to @NandoDF that started my career in ML (at the time I was a PM at Google) docs.google.com/document/d/1… Real effort (incl feedback) went into drafting it. Thanks to @EugeneVinitsky for nudging me to put it online
5
7
112
19,493
Our recently-accepted JMLR paper "Pathwise Conditioning of Gaussian Processes" is now live!
jmlr.org/papers/v22/20-1260.…
Check it out!
@mpd37
1
19
105
Call for new organizers - Seminar Series on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems!
If you're interested in organizing the next season - inviting speakers, telling people about the series, maybe putting together a workshop - please get in touch!
1
12
104
15,262
Today's NeurIPS reviews remind me that readers often focus on different things than authors.
My submission - which to me felt like some of my most solid work yet - received the worst reviews I've gotten in years.
Yet, this clearly isn't the reviewers' fault.. 1/3
2
2
100
P.S. - you should also consider Switzerland!
From talking to colleagues who study and work there, the scientific environment appears to be excellent, and may well be comparable to the one here.
3
3
93
15,862
One week after surgery.
Today, I managed to take a proper shower for the first time. Gradually starting to feel human again!
It’s also a big day for a second reason: my PhD viva, which I insisted on not postponing, will take place in the evening. Wish me luck!
7
100
Today, I finished a draft of the stochastic partial differential equation section in my thesis.
These are used to define Gaussian processes on non-Euclidean spaces, and calculate their covariance kernels - one of the key contributions.
I'm getting close to a full first draft!
1
1
96
We're looking for additional reviewers for the NeurIPS Workshop on Bayesian Decision-making and Uncertainty!
If you're willing to review 2 workshop paper submissions, please sign up - link below!
1
8
95
14,546
Excited to be organizing the NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning!
Check it out and consider submitting a 4-page workshop paper - extended abstract deadline is October 2nd.
@_mlutter @cosmo_shirley @wangleiphy
2
21
92
No, I am not doing okay today. There are so many things I want to talk about, but instead I'm at a loss for words, if not for my then for family's sake.
So, I'm left with nothing but picking meaningless Twitter fights about Kullback-Leibler divergences.
1
90
Happy NeurIPS deadline week!
One of my collaborators just discovered a mistake in one of my proofs.. 😭
How's your week going?
4
1
89
Let's talk about rejecting applicants who "did well in class". Every time we do that, we blanket exclude those not studying at top-tier research universities.
Many excellent students study at universities without a single active machine learning researcher in their department.
Application season is coming up! I wrote a post on "How to Ask for a Letter of Recommendation." Comments welcome. Feel free to share with anyone applying for grad school or jobs. tl;dr: Ask ppl you've done research w/ early & be organized! @AcademicChatter kamathematics.wordpress.com/…
2
9
83
Reminder that when NeurIPS papers are spuriously rejected, it wastes everyone's time:
* Authors do extra unnecessary work
* A whole new set of reviewers have to write reviews
To save time for us all, please read rebuttals carefully, correct misunderstandings, and score fairly.
5
10
82
10,511
I wanted to share another figure from my thesis before NeurIPS reviews arrive!
This one illustrates the class of pathwise-conditioning-based posterior Gaussian processes approximations we study, where the prior and update terms are approximated with finite basis expansions.
1
5
82
Software package announcement!
The Geometric Kernels package, which implements various geometric Gaussian process models from my papers - on manifolds, graphs, and similar - is now on PyPi!
It can be installed with `pip install geometric_kernels`.
Check it out!
Excited to announce a new release of GeometricKernels!
You can now install the package via `pip install geometric_kernels`!
Featuring new spaces, efficient GP sampling, and a much simpler interface, in addition to brand new tutorials & enhanced docs!
1
9
80
13,105
We've now got a blog post describing Matérn Gaussian Processes on Graphs, our AISTATS paper which won the "Best Student Paper" award, in detail.
avt.im/publications/2020/10/…
Check it out!
@mpd37 @NicolasDurrande
13
86
Very last last evening, I submitted the final version of my PhD thesis. I'll be sharing bits in the coming days - lots of pretty pictures to show!
In the meantime, I wanted to thank everyone who's been here and offered encouragement. You made the process so much more fun!
2
1
80
Time to showcase one of our AISTATS papers!
We study alignment of time series in different spaces - for instance, motion of a physical system in pixel space and coordinate space - using tools of optimal transport.
avt.im/publications/2020/06/…
@CohenSamuel13 @brandondamos @mpd37
1
14
81
Our paper “Matérn Gaussian Processes on Graphs” was selected for oral presentation at AISTATS! We’re still working on the blog post, but in the meantime check out the paper!
@NicolasDurrande @mpd37
arxiv.org/abs/2010.15538
3
7
82
I'm presenting three papers at NeurIPS - one spotlight, and one oral!
(2) "Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds" - spotlight poster - with Paul Rosa, Viacheslav Borovitskiy, and Judith Rousseau.
Short summary and links below!
1
2
75
12,983
It’s definitely discouraging to not even land an interview once during the course of my PhD, in spite of having plenty of publications and even awards for my research. I guess my research area isn’t interesting to people there who are hiring - I hope it’s interesting to others.
3
1
75
Last time, I showed you what the Matérn kernel defined on the surface of the dragon manifold looks like.
Here's what a posterior Gaussian process with that kernel, conditioned on training data, looks like!
Notice how the standard deviation grows as we move away from data!
2
7
71
I'm presenting three papers at NeurIPS - one spotlight and one oral!
(3) "Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent" - oral presentation - check out the linked blog post on this work!
Summary, authors, and links below!
papers.avt.im/stochastic-gra…
1
7
69
11,087
Averaging is a really good idea!
This idea was crucial in getting SGD for GPs to work, both in its original (papers.avt.im/stochastic-gra…) and refined (arxiv.org/abs/2310.20581) form, by removing learning rate schedules.
Geometric averaging works very well with multiplicative noise!
I often hear people who know optimization theory say
"averaging works assuming convexity, so it doesn't make sense for deep learning."
Yes it does, it just works. Often, it can replace learning rate scheduler. Just don't use uniform weights, use EMA or polynomial weights.
1
5
70
15,960
Oh man, where do I begin:
(1) My PhD was not funded by UK taxpayers.
(2) Gaussian processes do work, with direct scientific and commercial value for the UK and elsewhere. They are the only model class with which you can reliably built a working Bayesian optimization algorithm.
4
63
10,759
Today, I gave a brief tutorial on multi-armed bandits at UCL. Slides are available here: avt.im/talks/2021/03/04/Band….
If you missed it, don't worry! I'm giving the same tutorial again tomorrow at 12:30 UTC, and will hopefully not forget to record it that time.
1
13
70
The only reason probability is mysterious is because the usual ways of teaching it aggressively avoid the concept of random variable because it is "too abstract".
This is misguided. The concept is neither abstract, nor avoidable for purposes of understanding.
The notion of “probability” is both familiar (we use it), and mysterious (we would typically struggle to define it).
Here is a 🧵 to remove the mystery and make the meaning of “probability” more intuitive.
10
4
66
Scott Aaronson: "like the Jesuit astronomers declining to look through Galileo’s telescope, what Chomsky and his followers are ultimately angry at is reality itself, for having the temerity to offer something up that they didn’t predict and that doesn’t fit their worldview."
2
8
68
25,639
The problem with filling spots with those “already published” is that this is an incredibly strong proxy for “Harvard, Stanford, MIT, ..”
Undergraduates at institutions with no ML research labs, no advising, and no connection to the community have no chance.
This isn’t right.
I've the sense many students are legitimately concerned that most of the spots in CS grad admission will be filled with applicants who have publications already. The relevant question therefore is whether having publications is an overwhelming advantage, even if not necessary
4
3
68
The Journal of Machine Learning Research has clearly demonstrated that for-profit companies do not need to play a role of any kind in order to run a successful journal with no fees.
I encourage everyone who is on an Elsevier editorial board to resign immediately.
Dear @ResearchGate,
Thank you for your message and the threat to suspend my account. To avoid this from happening in the future, my group will never submit a paper to an #Elsevier journal again.
#OpenScience
Kind regards,
Prof. Wim Thiery
11
64
ML/Stats Twitter: does anyone understand why the convergence properties of K-means are so bad?
Is there an alternative clustering algorithm which runs in O(N) and can guarantee that nearby points are clustered while different clusters are separated?
8
5
61
As a postdoc starting soon at the University of Cambridge, I'm delighted to say that I'll be joining Sidney Sussex College as a College Research Associate!
@SidneySussex @Cambridge_Uni @CambridgeMLG @Postdoc_Academy
1
2
63
What I read: as a PhD applicant, the most important factor is which university you studied at - this determines both who writes your letters and what research opportunities, if any, you had available.
But what about all the talented people who didn’t have these opportunities?
I've been serving on grad admissions committees at MIT for 5 years - in EECS and Media Lab
If you want to get into a PhD at a place like MIT, here's a thread with some advice based on my observations
1/13
4
5
61
Thanks to everyone who participated in the NeurIPS Workshop on Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems!
At our poster session, I counted approximately 140 people - a spectacular success!
Lots of work, but well worth it.
gp-seminar-series.github.io/…
3
1
66
I've been interested in applying differential geometry to study machine learning problems with physical interpretations for some time now. These notes are the cleanest presentation I've seen yet of the geometric and physical aspects of this setup. bit.ly/328WN5l
16
62
The long-term consequence of big tech dismissing ethics and fairness concerns will be regulation and loss of control regarding what systems can be deployed and how data can be used. I wonder how much faster this will come as a result of @timnitGebru and @mmitchell_ai's firing?
2
14
53