5 citations · 10 across the 18 of their papers we have counts for
18 papers
Accelerating Speculative Diffusions via Block Verification
Alexander Soen, Hisham Husain, Valentin De Bortoli +1
Speculative decoding speeds up LLM inference by using a draft model to generate tokens, with an acceptance-rejection scheme that ensures that the output matches the target distribu…
Density-Ratio Losses for Post-Hoc Learning to Defer
Alexander Soen, Ragnar Thobaben, Joakim Jaldén +1
We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions: divergence-regularized reweightings of the data distribution under which a model attains low loss…
A Connection Between Learning to Reject and Bhattacharyya Divergences
Alexander Soen
Learning to reject provide a learning paradigm which allows for our models to abstain from making predictions. One way to learn the rejector is to learn an ideal marginal distribut…
Domain Adaptation and Entanglement: an Optimal Transport Perspective
Okan Koç, Alexander Soen, Chao-Kai Chiang +1
Current machine learning systems are brittle in the face of distribution shifts (DS), where the target distribution that the system is tested on differs from the source distributio…
pyBregMan: A Python library for Bregman Manifolds
Frank Nielsen, Alexander Soen
A Bregman manifold is a synonym for a dually flat space in information geometry which admits as a canonical divergence a Bregman divergence. Bregman manifolds are induced by smooth…
Online Learning in Betting Markets: Profit versus Prediction
Haiqing Zhu, Alexander Soen, Yun Kuen Cheung +1
We examine two types of binary betting markets, whose primary goal is for profit (such as sports gambling) or to gain information (such as prediction markets). We articulate the in…
Rejection via Learning Density Ratios
Alexander Soen, Hisham Husain, Philip Schulz +1
Classification with rejection emerges as a learning paradigm which allows models to abstain from making predictions. The predominant approach is to alter the supervised learning pi…
3D NLTE Lithium abundances for late-type stars in GALAH DR3
Ella Xi Wang, Thomas Nordlander, Sven Buder +7
Lithium's susceptibility to burning in stellar interiors makes it an invaluable tracer for delineating the evolutionary pathways of stars, offering insights into the processes gove…
Trade-Offs of Diagonal Fisher Information Matrix Estimators
Alexander Soen, Ke Sun
The Fisher information matrix can be used to characterize the local geometry of the parameter space of neural networks. It elucidates insightful theories and useful tools to unders…
Tempered Calculus for ML: Application to Hyperbolic Model Embedding
Richard Nock, Ehsan Amid, Frank Nielsen +2
Most mathematical distortions used in ML are fundamentally integral in nature: -divergences, Bregman divergences, (regularized) optimal transport distances, integral probability…
Sampled Transformer for Point Sets
Shidi Li, Christian Walder, Alexander Soen +2
The sparse transformer can reduce the computational complexity of the self-attention layers to , whilst still being a universal approximator of continuous sequence-to-sequenc…
Fair Wrapping for Black-box Predictions
Alexander Soen, Ibrahim Alabdulmohsin, Sanmi Koyejo +5
We introduce a new family of techniques to post-process ("wrap") a black-box classifier in order to reduce its bias. Our technique builds on the recent analysis of improper loss fu…
Linking Across Data Granularity: Fitting Multivariate Hawkes Processes to Partially Interval-Censored Data
Pio Calderon, Alexander Soen, Marian-Andrei Rizoiu
The multivariate Hawkes process (MHP) is widely used for analyzing data streams that interact with each other, where events generate new events within their own dimension (via self…
On the Variance of the Fisher Information for Deep Learning
Alexander Soen, Ke Sun
In the realm of deep learning, the Fisher information matrix (FIM) gives novel insights and useful tools to characterize the loss landscape, perform second-order optimization, and…
Interval-censored Hawkes processes
Marian-Andrei Rizoiu, Alexander Soen, Shidi Li +4
Interval-censored data solely records the aggregated counts of events during specific time intervals - such as the number of patients admitted to the hospital or the volume of vehi…
Fair Densities via Boosting the Sufficient Statistics of Exponential Families
Alexander Soen, Hisham Husain, Richard Nock
We introduce a boosting algorithm to pre-process data for fairness. Starting from an initial fair but inaccurate distribution, our approach shifts towards better data fitting while…
UNIPoint: Universally Approximating Point Processes Intensities
Alexander Soen, Alexander Mathews, Daniel Grixti-Cheng +1
Point processes are a useful mathematical tool for describing events over time, and so there are many recent approaches for representing and learning them. One notable open questio…
Influence Flowers of Academic Entities
Minjeong Shin, Alexander Soen, Benjamin T. Readshaw +3
We present the Influence Flower, a new visual metaphor for the influence profile of academic entities, including people, projects, institutions, conferences, and journals. While ma…