Sergei Vassilvitskii

[Jalaj Upadhyay @jalajupadhyay]

The third iteration of NYC Privacy Day is going to happen this October. Register and learn about the cutting-edge work done in security and privacy in the last few months :) https://t.co/vUNSAI402H

[Sergei Vassilvitskii @vsergei]

@_onionesque @aryehazan It's almost 16 years old at this point (soda 2007).

[Sergei Vassilvitskii @vsergei]

@aryehazan The history of original k-means is interesting, but won't fit in the margins of this tweet. However, k-means++ as the now standard way to initialize k-means did come from theory.

[Michael Dinitz @mdinitz]

Another new paper on the arxiv to talk about: https://t.co/TigTtrooAF . This paper is my first foray into differential privacy, which was fun and forced me to learn a lot.

[Michael Dinitz @mdinitz]

New paper just hit the arxiv, and which was one of the most fun and interesting research projects that I've ever worked on: https://t.co/nnCfhcsizL . Long story short, we found some super interesting and surprising behavior in the most well-studied online problems: ski rental!

[Alexey Kurakin @alexey2004]

Training ML models with differential privacy could be challenging.
To aid practitioners, we wrote a detailed survey with known best practices of DP-training of ML models: https://t.co/RtW5VyAdRh

[Michael Dinitz @mdinitz]

Super excited about a new preprint, "Faster Matchings via Learned Duals", with Sungjin Im, Thomas Lavastida, Ben Moseley, and @vsergei . Long story short: we can use ML to massively speed up min-cost perfect matching computations! https://t.co/KYRlIWPHle

[Constantinos Daskalakis @KonstDaskalakis]

A great line-up for the July 13-14 FODSI workshop on ML for Algos! @AlexGDimakis-Yonina Eldar-@annadgoldie-@HeckelReinhard-Stephanie Jegelka-@tim_kraska-Benjamin Moseley-David Parkes-@AlgoSvensson-Tuomas Sandholm-@vsergei-Ellen Vitercik-David Woodruff!

https://t.co/99UVdVv7LF

[TCS blog aggregator @cstheory]

Algorithms with Predictions: Survey and Workshop https://t.co/XJxFzeLts8

[Sergei Vassilvitskii @vsergei]

@amitc1 @geomblog @RikSarkarNet @chaturv3di Book!

[Sergei Vassilvitskii @vsergei]

@Aaroth A nice simple exercise. Suppose you are estimating the mean of a Gaussian distribution from iid samples. Compare the DP error to the finite sample error. TL;DR; with DP you need O(\sqrt{log n}) more samples to get parity.

[Sergei Vassilvitskii @vsergei]

@dsivakumar @ravik53 @JeffDean Don't forget @ssuri ! Nailing down the model of computation took many coffees and whiteboard sessions

[Sergei Vassilvitskii @vsergei]

@moyix @bipr Cc @jakehofman

[Sergei Vassilvitskii @vsergei]

Coming out of twitter hibernation to say that part 1 of the clustering book with @geomblog is available at https://t.co/jLwrKXiobf !

As we say in the intro: Clustering is more than just a collection of tools...
it is a systematic way to think about how data should be organized.

[Sergei Vassilvitskii @vsergei]

@bipr Too bad the supervised learning session is in a different room

[Sergei Vassilvitskii @vsergei]

@geomblog Strongly sublinear? Though we used that to distinguish n^\delta from n/\log n.

[Sergei Vassilvitskii @vsergei]

@nikete @haldaume3 what's coming online, points or dimensions? Shameless plug from aistats16 https://t.co/hneVh9VwV1

[Sergei Vassilvitskii @vsergei]

. @dggoldst @jakehofman nicely done!

[import Grigory.ai Yaroslavtsev 🇺🇲 @gyaroslavtsev]

Joint effort with Sergei Vassilvitskii: "Parallel Models: (Hitchhiker's Guide to Massively Parallel Universes)": http://t.co/rSNDmPcCs6