Justin Curry
@currying
Followers
2K
Following
5K
Media
83
Statuses
1K
Associate Professor of Math & Statistics at UAlbany-SUNY
Albany, New York, USA
Joined November 2009
Very nice exposition of a recent cover learning technique that deserves more attention! https://t.co/RyZE2Ilk86
luisscoccola.com
The standard approach to Topological Inference is based on geometric complexes. Most commonly, geometric complexes scale cubically (and often worse) in the number of data points, which poses a big...
0
0
5
@IntuitMachine ......here's the link to the paper for those actually wanting to check it out:
1
4
31
@obadafidi_dada @shri_shobhit Oh yeah, while programming seems important for crystalization, but it does not seem to be THE critical step. Just came across this: https://t.co/bPJ8NnsBTe cc: @mymyw_ @MarathiDebate
0
15
133
Rob is a poet. I've known this since seeing him wax theological on Spherical Geometries at the Philomathean Society in '09; a place of resonance between us. Read below where it says "I was in a Printing-House in Hell..." to get a better sense of Rob and his poetic explorations
the last chapter of my book "The Geometry of Heaven & Hell" is an homage to blake's marriage of heaven & hell, and, though not quite isomorphic to it, nevertheless rhymes with the original... a bit of background: the book posits that poets, in imagining spaces beyond life &
0
0
2
Eager to dig into this!
new preprint: arithmetic barcodes for network sheaves over p-adic integers 🔗 https://t.co/ocI5Nd1uRQ persistent homology filters by geometric scale. we filter by algebraic precision instead: ℤ_p ⊇ pℤ_p ⊇ p²ℤ_p ⊇ ⋯ torsion summands ℤ_p/p^a become bars of length a,
0
0
2
An inductive mean is a mean obtained as a limit of a converging sequence of other means like the arithmetic-geometric mean or the arithmetic-harmonic mean Build inductive means for complex numbers, matrices, functions, etc. "What is... an inductive mean?" (AMS Notices)
2
38
311
Chen, Jebelli, Rockmore: Curvature of high-dimensional data https://t.co/2PE6HLWIiC
https://t.co/WD9e1hfOuM
arxiv.org
We consider the problem of estimating curvature where the data can be viewed as a noisy sample from an underlying manifold. For manifolds of dimension greater than one there are multiple...
0
10
68
when i presented clrs at stanford, a fun question arose that i didn't get anywhere else: 'would pre-training a gnn to execute algorithms help on an ogb task?' it... took a while before this got checked, but thanks to Jason (my cambridge student), we now know the answer is yes 😄
4
9
65
[LG] The Geometry of Reasoning: Flowing Logics in Representation Space Y Zhou, Y Wang, X Yin, S Zhou... [Duke University] (2025) https://t.co/63YfIjsztN
1
27
157
I sent an email to P. Diaconis yesterday to tell him how much I liked his paper ‘Generating a Random Permutation with Random Transpositions’ (1981), and that our work below was inspired by it. He actually replied, which is awesome! He also pointed me to another application of
arxiv.org
Let $\mathcal{S}_n$ be the permutation group on $n$ elements, and consider a random walk on $\mathcal{S}_n$ whose step distribution is uniform on $k$-cycles. We prove a well-known conjecture that...
On the Statistical Query Complexity of Learning Semiautomata: a Random Walk Approach Work with @ggiapitz, @EshaanNichani and @jasondeanlee. We prove the first SQ hardness result for learning semiautomata under the uniform distribution over input words and initial states,
2
6
121
"Mathematical Structures: From Linear Algebra over Rings to Geometry with Sheaves" https://t.co/K0PkkTTC3U
5
93
557
Singular learning theory is a theory of machine learning of singular models, either non-identifiable models or having degenerate Fisher information matrix. Regular non-singular statistical models are handled as manifolds and singular models as algebraic varieties
4
77
570
instead of trying to get AI to prove the Big Conjecture, here's something you can do right now with high odds of success... the hidden 💎 search for math papers by profs at a top uni that are >5 years out and have <10 citations. pull up a stack of 'em. feed the stack to
13
20
260
In "On Growth and Form," published in 1917, the scientist D’Arcy Thompson highlighted similarities between living and nonliving matter. His thesis — that physical and mechanical forces shape organisms — is coming back into vogue. https://t.co/MqZFyXgh71
15
142
694
when it rains, it pours! for years, it seemed like the ML community had lost interest in PAC learning automata and formal languages the topic had seemed "exhausted" -- mainly because essentially any reasonable thing you'd want to do was proven to be computationally hard in some
7
12
108
Beautiful piece in the AMS notices
An inductive mean is a mean obtained as a limit of a converging sequence of other means like the arithmetic-geometric mean or the arithmetic-harmonic mean Build inductive means for complex numbers, matrices, functions, etc. "What is... an inductive mean?" (AMS Notices)
0
0
0