papers

Publications (17)

cs.LG2025

Efficient Learning With Sine-Activated Low-rank Matrices

Yiping Ji, Hemanth Saratchandran, Cameron Gordon +2

Low-rank decomposition has emerged as a vital tool for enhancing parameter efficiency in neural network architectures, gaining traction across diverse applications in machine learn…

cs.DC2024

Distributed Genetic Algorithm for Feature Selection

Michael Potter, Ayberk Yarkın Yıldız, Nishanth Marer Prabhu +1

We empirically show that process-based Parallelism speeds up the Genetic Algorithm (GA) for Feature Selection (FS) 2x to 25x, while additionally increasing the Machine Learning (ML…

cs.LG2026

Memory Efficient Tabular Foundation Models

Shuting Luo, Monika Mikhail Kanaan, Cameron Gordon +2

The paper studies how to reduce the memory footprint of tabular foundation models like TabPFN using compression techniques, achieving up to 7.6× memory savings with little performa…

#tabular data#foundation models#model compression#memory efficiency
math.GT2017

Taut foliations, left-orderability, and cyclic branched covers

Cameron Gordon, Tye Lidman

We study the question of when cyclic branched covers of knots admit taut foliations, have left-orderable fundamental group, and are not L-spaces.

cs.LG2024

D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations

Cameron Gordon, Lachlan Ewen MacDonald, Hemanth Saratchandran +1

Deep implicit functions have been found to be an effective tool for efficiently encoding all manner of natural signals. Their attractiveness stems from their ability to compactly r…

math.GT2012

Obtaining genus 2 Heegaard splittings from Dehn surgery

Kenneth L Baker, Cameron Gordon, John Luecke

Let K' be a hyperbolic knot in S^3 and suppose that some Dehn surgery on K' with distance at least 3 from the meridian yields a 3-manifold M of Heegaard genus 2. We show that if M…

math.GR2009

On surface subgroups of doubles of free groups

Cameron Gordon, Henry Wilton

We give several sufficient conditions for a double of a free group along a cyclic subgroup to contain a surface subgroup.

math.GT2013

Bridge number and integral Dehn surgery

Ken Baker, Cameron Gordon, John Luecke

In a 3-manifold M, let K be a knot and R be an annulus which meets K transversely. We define the notion of the pair (R,K) being caught by a surface Q in the exterior of the link gi…

math.GT2012

Knots with small rational genus

Danny Calegari, Cameron Gordon

If K is a rationally null-homologous knot in a 3-manifold M, the rational genus of K is the infimum of -χ(S)/2p over all embedded orientable surfaces S in the complement of K whos…

cs.SI2022

The Information Bottleneck Principle in Corporate Hierarchies

Cameron Gordon

The hierarchical nature of corporate information processing is a topic of great interest in economic and management literature. Firms are characterised by a need to make complex de…

cs.LG2025

From Tables to Signals: Revealing Spectral Adaptivity in TabPFN

Jianqiao Zheng, Cameron Gordon, Yiping Ji +2

Task-agnostic tabular foundation models such as TabPFN have achieved impressive performance on tabular learning tasks, yet the origins of their inductive biases remain poorly under…

cs.AI2026

Mask-Based Priors Are More Persistent than Query-Key Initializations

Mingze Ma, Hemanth Saratchandran, Cameron Gordon +1

Transformers do not merely lack data on some Boolean extrapolation tasks; they generalize in a systematically wrong way. Recent work on generalization on the unseen has shown that,…

math.GT2013

Bridge number, Heegaard genus and non-integral Dehn surgery

Kenneth L. Baker, Cameron Gordon, John Luecke

We show there exists a linear function w: N->N with the following property. Let K be a hyperbolic knot in a hyperbolic 3-manifold M admitting a non-longitudinal S^3 surgery. If K i…

cs.LG2025

SineLoRA: Sine-Activated Delta Compression

Cameron Gordon, Yiping Ji, Hemanth Saratchandran +2

Resource-constrained weight deployment is a task of immense practical importance. Recently, there has been interest in the specific task of \textit{Delta Compression}, where partie…

cs.CV2022

On Quantizing Implicit Neural Representations

Cameron Gordon, Shin-Fang Chng, Lachlan MacDonald +1

The role of quantization within implicit/coordinate neural networks is still not fully understood. We note that using a canonical fixed quantization scheme during training produces…

math.GR2011

On the divisibility of $#\Hom(Γ,G)$ by $|G|

Fernando Rodriguez Villegas, Cameron Gordon

We extend and reformulate a result of Solomon on the divisibility of the title. We show, for example, that if is a finitely generated group, then divides $#\Hom(Γ,G)$ f…

math.GT2015

Knot contact homology detects cabled, composite, and torus knots

Cameron Gordon, Tye Lidman

Knot contact homology is an invariant of knots derived from Legendrian contact homology which has numerous connections to the knot group. We use basic properties of knot groups to…