Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Which recent research paper blew your mind?

news.ycombinator.com

Post reply on HN
Print view View original

31–40 of 174 posts

Re: Ask HN: Which recent research paper blew your mind?

#31

Post by GregarianChild »

claytonjy wrote: post #19
GregarianChild wrote: post #10

Someone managed to GPU-accelerate program synthesis, a form of symbolic ML. First time for ML that is not deep learning: https://dl.acm.org/doi/10.1145/3591274 Deep learning took off precisely when the ImageNet paper dropped around 2010. Before nobody believed that backprop can be GPU-accelerated.

> First time for ML that is not deep learning What do you mean by this? Virtually all "classic" or "shallow" ML can be GPU-accelerated, from linear regression to SVM to GBM.

Can you point me to papers with reproducible benchmarking that achieves big speedups on those?

Modern GPUs are GP-GPUs: where GP means "general purpose": you can run any code on GPGPUs. But if you want to gain real speed-ups you will have to program in an awkward style ("data parallel"). I am not aware of GPU acceleration of the work-horses of symbolic AI, such as Prolog, or SMT solving. There has been a lot of work on running SAT-solvers on GPUs, but I don't think this has really succeeded so far.

Re: Ask HN: Which recent research paper blew your mind?

#32

Post by pavo-etc »

edent wrote: post #17

"Overview of SHARD: A System for Highly Available Replicated Data" it's the first paper to introduce the concept of database sharding. It was published in 1988 by the Computer Corporation of America. It is referenced hundreds of times in many classic papers. But, here's the thing. It doesn't exist . Everyone cites Sarin, DeWitt & Rosenb[e|u]rg's paper but none have ever seen it. I've emailed dozens of academics, libr…

Wow this is fascinating. Are any of these authors still alive?

Re: Ask HN: Which recent research paper blew your mind?

#33

Post by jjoonathan »

paxys wrote: post #15
the_snooze wrote: post #3

"Blue Is the New Black (Market): Privacy Leaks and Re-Victimization from Police-Auctioned Cellphones" https://krebsonsecurity.com/2023/05/re-victimization-from-po... Researchers bought up a bunch of seized phones from police auction sites and found about 25% of them were trivially unlockable and still held sensitive data about suspects and victims .

Is this really "mind blowing"? Knowing the competency of the average police department, I'd consider it more par for the course.

Novelty is overrated. Finding proof and pushing for accountability is so much more important.

Re: Ask HN: Which recent research paper blew your mind?

#34

Post by Silamoth »

I recently read "Enabling tabular deep learning when d ≫ n with an auxiliary knowledge graph" (https://arxiv.org/pdf/2306.04766.pdf) for one of my graduate classes. Essentially, when there are significantly more data points than features (n >> d), machine learning usually works fine (assuming data quality, an underlying relationship, etc.). But, for sparse datasets where there are fewer data points than features (d >> n), most machine learning methods fail. There's just not enough data to learn all the relationships. This paper builds a knowledge graph based on relationships and other pre-existing knowledge of data features to improve model performance in this case. It's really interesting - I hadn't realized there were ways to get better performance in this case.

Re: Ask HN: Which recent research paper blew your mind?

#35

Post by leonheld »

edent wrote: post #17

"Overview of SHARD: A System for Highly Available Replicated Data" it's the first paper to introduce the concept of database sharding. It was published in 1988 by the Computer Corporation of America. It is referenced hundreds of times in many classic papers. But, here's the thing. It doesn't exist . Everyone cites Sarin, DeWitt & Rosenb[e|u]rg's paper but none have ever seen it. I've emailed dozens of academics, libr…

I think this is your blog, so I'm going to post it here because it is so great to look at!

https://shkspr.mobi/blog/2021/06/where-is-the-original-overv...

Re: Ask HN: Which recent research paper blew your mind?

#36

Post by dicroce »

w-m wrote: post #26

Integral Neural Networks (CVPR 2023 Award Candidate), a nifty way of building resizable networks. My understanding of this work: A forward pass for a (fully-connected) layer of a neural network is just a dot product of the layer input with the layer weights, followed by some activation function. Both the input and the weights are vectors of the same, fixed size. Let's imagine that the discrete values that form these…

Damn. It's like jpeg for neural networks.

Re: Ask HN: Which recent research paper blew your mind?

#37

Post by chubot »

edent wrote: post #17

"Overview of SHARD: A System for Highly Available Replicated Data" it's the first paper to introduce the concept of database sharding. It was published in 1988 by the Computer Corporation of America. It is referenced hundreds of times in many classic papers. But, here's the thing. It doesn't exist . Everyone cites Sarin, DeWitt & Rosenb[e|u]rg's paper but none have ever seen it. I've emailed dozens of academics, libr…

Which papers cite it? Are they old papers, when perhaps it still existed, or recent ones?

Very interesting either way!

Re: Ask HN: Which recent research paper blew your mind?

#38

Post by antegamisou »

edent wrote: post #17

"Overview of SHARD: A System for Highly Available Replicated Data" it's the first paper to introduce the concept of database sharding. It was published in 1988 by the Computer Corporation of America. It is referenced hundreds of times in many classic papers. But, here's the thing. It doesn't exist . Everyone cites Sarin, DeWitt & Rosenb[e|u]rg's paper but none have ever seen it. I've emailed dozens of academics, libr…

> It is referenced hundreds of times in many classic papers.

According to Google Scholar, it's cited a measly 11 times .

https://scholar.google.com/scholar?cites=1491448744595502026...

Re: Ask HN: Which recent research paper blew your mind?

#40

Post by cinericius »

yung_steezy wrote: post #18
edent wrote: post #17

"Overview of SHARD: A System for Highly Available Replicated Data" it's the first paper to introduce the concept of database sharding. It was published in 1988 by the Computer Corporation of America. It is referenced hundreds of times in many classic papers. But, here's the thing. It doesn't exist . Everyone cites Sarin, DeWitt & Rosenb[e|u]rg's paper but none have ever seen it. I've emailed dozens of academics, libr…

Is this an example of reference rot or did it never exist?

If it did exist, there's some delicious irony in an original paper on replicating data in a highly-available manner being lost.
Post reply on HN