27 citations · 57 across the 10 of their papers we have counts for
14 papers
Stochastic Optimization Under Power-Law Spectra: Tight Bounds and Shuffling Analysis
Thomas Dybdahl Ahle, Yaroslav Bulatov, Christopher De Sa +1
Recent work has established that power-law spectral conditions on data enable tight convergence bounds for deterministic gradient descent, resolving the conflict between classical…
Error Mitigation for Thermodynamic Computing
Maxwell Aifer, Denis Melanson, Kaelan Donatella +3
While physics-based computing can offer speed and energy efficiency compared to digital computing, it also is subject to errors that must be mitigated. For example, many error miti…
Thermodynamic Computing System for AI Applications
Denis Melanson, Mohammad Abu Khater, Maxwell Aifer +7
Recent breakthroughs in artificial intelligence (AI) algorithms have highlighted the need for novel computing hardware in order to truly unlock the potential for AI. Physics-based…
Favour: FAst Variance Operator for Uncertainty Rating
Thomas D. Ahle, Sahar Karimi, Peter Tak Peter Tang
Bayesian Neural Networks (BNN) have emerged as a crucial approach for interpreting ML predictions. By sampling from the posterior distribution, data scientists may estimate the unc…
Thermodynamic Matrix Exponentials and Thermodynamic Parallelism
Samuel Duffield, Maxwell Aifer, Gavin Crooks +2
Thermodynamic computing exploits fluctuations and dissipation in physical systems to efficiently solve various mathematical problems. For example, it was recently shown that certai…
Thermodynamic Linear Algebra
Maxwell Aifer, Kaelan Donatella, Max Hunter Gordon +5
Linear algebraic primitives are at the core of many modern algorithms in engineering, science, and machine learning. Hence, accelerating these primitives with novel computing hardw…
Clustering the Sketch: A Novel Approach to Embedding Table Compression
Henry Ling-Hei Tsang, Thomas Dybdahl Ahle
Embedding tables are used by machine learning systems to work with categorical features. In modern Recommendation Systems, these tables can be very large, necessitating the develop…
The Power of Hashing with Mersenne Primes
Thomas Dybdahl Ahle, Jakob Tejs Bæk Knudsen, Mikkel Thorup
The classic way of computing a -universal hash function is to use a random degree- polynomial over a prime field . For a fast computation of the polynomial,…
Similarity Search with Tensor Core Units
Thomas D. Ahle, Francesco Silvestri
Tensor Core Units (TCUs) are hardware accelerators developed for deep neural networks, which efficiently support the multiplication of two dense matrices,…
On the Problem of in Locality-Sensitive Hashing
Thomas Dybdahl Ahle
A Locality-Sensitive Hash (LSH) function is called -sensitive, if two data-points with a distance less than collide with probability at least while data p…
Subsets and Supermajorities: Optimal Hashing-based Set Similarity Search
Thomas Dybdahl Ahle, Jakob Bæk Tejs Knudsen
We formulate and optimally solve a new generalized Set Similarity Search problem, which assumes the size of the database and query sets are known in advance. By creating polylog co…
Optimal Las Vegas Locality Sensitive Data Structures
Thomas Dybdahl Ahle
We show that approximate similarity (near neighbour) search can be solved in high dimensions with performance matching state of the art (data independent) Locality Sensitive Hashin…
Parameter-free Locality Sensitive Hashing for Spherical Range Reporting
Thomas D. Ahle, Martin Aumüller, Rasmus Pagh
We present a data structure for *spherical range reporting* on a point set , i.e., reporting all points in that lie within radius of a given query point . Our solutio…
On the Complexity of Inner Product Similarity Join
Thomas D. Ahle, Rasmus Pagh, Ilya Razenshteyn +1
A number of tasks in classification, information retrieval, recommendation systems, and record linkage reduce to the core problem of inner product similarity join (IPS join): ident…