If you're a PhD student interested in interning with me or one of my amazing colleagues at Microsoft Research New England (
@MSRNE
,
@MSFTResearch
) this summer, please apply here
@bremen79
You can also use “empirical Berry Esseen bounds” to get both finite sample validity and asymptotic efficiency (matching the optimal CLT-based width in the limit)
“Recursive self-improvement” (RSI) is one of the oldest ideas in AI. Can language models write code that recursively improves itself?
Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generation
w/
@elianalorch
,
@LesterMackey
,
@adamfungi
(1/n)
Super excited to present “Kernel Thinning”, a new procedure for compressing a distribution more effectively than i.i.d. sampling or standard MCMC thinning. w/
@LesterMackey
, today 2PM ET@
#MCM
, tomorrow 10AM/Noon@
#COLT2021
Video:
@risteski_a
This looks great
@risteski_a
! See also Minimum Stein Discrepancy Estimators () for an analysis of score matching (and related procedures like diffusion score matching)
@Avipartho1
@MSRNE
@MSFTResearch
These letters often come from a PhD advisor or other collaborators or research mentors who can speak to your research experience
tl;dr: A low-cost machine learning correction for physics-based dynamical models improves subseasonal forecasting of temperature and precipitation two to six weeks ahead.
@shortstein
The matrix Hoeffding inequality (Cor. 4.2 of ) would give you P( twonorm(sum_i X_i) >= t ) <= (d+1) exp( - t^2 / sum_i c_i^2 ) . There are also ways to get rid of that d multiplier
@prabhantsingh
From the Application Action Center, you should be able to request references, see the status of your submission, and request updated versions of letters. Please send me an email if you're running into trouble!
@joe_sill
This is still my favorite: "Hi Lester,
Lowes Foods has an opening for a Sausage Professor in their Town of Mount Pleasant location. We thought you might be interested in this opportunity.
Have a great day."
@lizbwood
I couldn't understand why it was struggling so hard to write poetry with a certain meter, and I guess the answer is... ChatGPT doesn't know what a syllable is