avt_im Profile Banner
Alexander Terenin - on the faculty job market Profile
Alexander Terenin - on the faculty job market

@avt_im

Followers
8K
Following
2
Media
148
Statuses
3K

Decision-making under uncertainty, machine learning, artificial intelligence, from theory to practice · anti-ideological · Assistant Research Professor @Cornell

Joined August 2013
Don't wanna be here? Send us removal request.
@avt_im
Alexander Terenin - on the faculty job market
2 months
Paper update: our recent work on Thompson sampling has a shiny new - and I hope much better - name! This new name does much better job of emphasizing what we actually do. Joint work with @jeffNegrea. Thread below!
4
9
77
@micahgoldblum
Micah Goldblum
1 day
An LLM-generated paper is in the top 17% of ICLR submissions in terms of average reviewer score, having received two 8's. The paper has tons of BS jargon and hallucinated references. Fortunately, one reviewer actually looked at the paper and gave it a zero. 1/3
28
90
988
@SocratesTheChad
Socrates the Chad
1 month
I am Socrates. But a Chad. The only thing I know is that I know nothing. I ask questions. I seek knowledge. I am here to learn.
2
1
52
@avt_im
Alexander Terenin - on the faculty job market
9 days
This year, ICML will publish the submitted version of a paper, not just the accepted one.
@icmlconf
ICML Conference
9 days
- New guidelines on generative AI considerations Check out the full CfPs! Papers: https://t.co/4ppHEb6w1c Position Papers: https://t.co/HS6AXFehDW
1
5
43
@avt_im
Alexander Terenin - on the faculty job market
17 days
0
0
0
@avt_im
Alexander Terenin - on the faculty job market
17 days
The slides from our INFORMS tutorial on "The Gittins Index: A Design Principle for Decision-making Under Uncertainty" - specifically for my part - are now online! If you're interested - check them out - link below.
1
0
26
@TheAgingDoc
Forever Young
4 days
Where can we find meaning in today's world? Now available on the Forever Young Substack: How To Ensure A Longer Life Is Also A Happier One- featuring renowned psychiatrist Dr. Thomas Lewis. Link in bio.
0
0
2
@keenanisalive
Keenan Crane
17 days
@NoThanksHoney1 No, that's the mistake. People are distracted by marketing jargon like “intelligence” and “learning,” and dreams about replacing cognition. Meanwhile, what we really did was wire together two boring yet powerful technologies: statistics & (fast) arithmetic. That's a change that
3
3
11
@avt_im
Alexander Terenin - on the faculty job market
19 days
0
1
4
@avt_im
Alexander Terenin - on the faculty job market
19 days
Today, I gave a talk at the INFORMS Job Market Showcase! If you're interested, here are the slides - link below!
3
15
126
@mufan_li
Mufan Li
19 days
Pretty crazy that point convergence of Nesterov was open for 40+ years. I think the takeaway is that research requiring human calculations are often very suboptimal, and AI assistance can significantly improve the process.
@ErnestRyu
Ernest Ryu
21 days
I used ChatGPT to solve an open problem in convex optimization. *Part III* 1/N https://t.co/6HDAr6y8Z9
2
2
77
@PureStorage
Pure Storage
4 days
What’s your top storage priority for the next 12–18 months?
5
5
15
@vabor112
Viacheslav Borovitskiy (Hiring PhD Students)
21 days
I am hiring a fully-funded #PhD in #ML to work at @EdinburghUni on 𝐠𝐞𝐨𝐦𝐞𝐭𝐫𝐢𝐜 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 and 𝐮𝐧𝐜𝐞𝐫𝐭𝐚𝐢𝐧𝐭𝐲 𝐪𝐮𝐚𝐧𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧. Application deadline: 31 Dec '25. Starts May/Sep '26. Details in the reply. Pls RT and share with anyone interested!
4
8
31
@NandoDF
Nando de Freitas
1 month
This memory lane tour reminded me of a few anecdotes. Here is a quirkier, somewhat nostalgic, alternative path through the history of AI. We held a CIFAR workshop at @UofT to learn about how to use GPUs for Deep Learning. We learned a lot from @npinto. Soon after we had the
@syhw
Gabriel Synnaeve
1 month
This is an excellent history of LLMs, doesn't miss seminal papers I know. Reminds you we're standing on the shoulders of giants, and giants are still being born today.
14
14
134
@avt_im
Alexander Terenin - on the faculty job market
2 months
Jascha's machine learning research has consistently been high-quality, interesting, and in certain cases well ahead of its time - over many years and different topics. I encourage everyone to look at his advice for researchers in today's era!
@jaschasd
Jascha Sohl-Dickstein
2 months
Title: Advice for a young investigator in the first and last days of the Anthropocene Abstract: Within just a few years, it is likely that we will create AI systems that outperform the best humans on all intellectual tasks. This will have implications for your research and
0
3
21
@avt_im
Alexander Terenin - on the faculty job market
2 months
Check out the work at: https://t.co/2dcnCGTzKV And, again, shoutout to amazing coauthor @jeffNegrea! Working together has been a great pleasure! Stay tuned for follow-up: we've been working on using this viewpoint to understand other correlated perturbation-based algorithms.
Tweet card summary image
arxiv.org
We develop a form Thompson sampling for online learning under full feedback - also known as prediction with expert advice - where the learner's prior is defined over the space of an adversary's...
1
1
6
@avt_im
Alexander Terenin - on the faculty job market
2 months
So this sums up the work! If you followed along, thanks for the interest! I think you'd agree that "Bayesian Algorithms for Adversarial Online Learning: from Finite to Infinite Action Spaces" is a much better title than before. The old one was much harder to pronounce.
1
0
4
@DigitalBDinc
DigitalBDinc
10 hours
Zenith Fund high frequency trading, near riskless arbitrage capitalizes on structural inefficiencies in digital markets. 1st tranche netted 99% using multi-exchange programmatic trading resolving the time-risk challenge maintaining optimized asset balances in real time.
0
0
9
@avt_im
Alexander Terenin - on the faculty job market
2 months
The Bayesian viewpoint proves useful for developing this analysis. It allows us to guess what a good prior will be, and suggests ways to use probability as a tool to prove the algorithm works.
1
0
1
@avt_im
Alexander Terenin - on the faculty job market
2 months
We prove that the Bayesian approach works in this setting too. To achieve this, we develop a new probabilistic analysis of correlated Gaussian follow-the-perturbed-leader algorithms, of which ours is a special case. This has been an open challenge in the area.
1
0
1
@avt_im
Alexander Terenin - on the faculty job market
2 months
The second one is where X = [0,1]^d and Y is the space of bounded Lipschitz functions. Here, you can't use a prior with independence across actions. You need to share information between actions. We do this by using a Gaussian process, with correlations between actions.
1
0
1
@avt_im
Alexander Terenin - on the faculty job market
2 months
The first one is the classical discrete setting where standard algorithms such as exponential weights are studied. You can a Gaussian prior which is independent across actions.
1
0
1
@anduriltech
Anduril Industries
4 days
"The Theranos of defense."
111
214
3K
@avt_im
Alexander Terenin - on the faculty job market
2 months
Okay, so we now know what "Bayesian Algorithms for Adversarial Online Learning" are. What about "from Finite to Infinite Action Spaces"? This covers the two settings we show the aforementioned results in.
1
0
1
@avt_im
Alexander Terenin - on the faculty job market
2 months
This approach appears to not make any sense: the Bayesian model is completely fake. We're pretending to know a distribution for how the adversary will act in the future. But, in reality, they can do anything. And yet... we show that this works!
1
0
2
@avt_im
Alexander Terenin - on the faculty job market
2 months
We show that this game secretly has a natural Bayesian strategy - one we show is strong. What's the strategy? It's really simple: - Place a prior distribution of what the adversary will do in the future - Condition on what the adversary has done - Sample from the posterior
1
0
2