32 citations · 70 across the 12 of their papers we have counts for
13 papers
Model Merging on Loss Landscape: A Geometry Perspective
Juanwu Lu, Anand Bhaskar, Brian Axelrod +2
Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscap…
Gradient-Stable Attention Heads Signal LLM Correctness
Sophie Ostmeier, Brian Axelrod, Maya Varma +6
Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evaluation is expensive, and LLM-as-ju…
LieRE: Lie Rotational Positional Encodings
Sophie Ostmeier, Brian Axelrod, Maya Varma +3
Transformer architectures rely on position encodings to model the spatial structure of input data. Rotary Position Encoding (RoPE) is a widely used method in language models that e…
Random Expert Sampling for Deep Learning Segmentation of Acute Ischemic Stroke on Non-contrast CT
Sophie Ostmeier, Brian Axelrod, Benjamin Pulli +6
Purpose: Multi-expert deep learning training methods to automatically quantify ischemic brain tissue on Non-Contrast CT Materials and Methods: The data set consisted of 260 Non-Con…
Non-inferiority of Deep Learning Acute Ischemic Stroke Segmentation on Non-Contrast CT Compared to Expert Neuroradiologists
Sophie Ostmeier, Brian Axelrod, Benjamin F. J. Verhaaren +7
To determine if a convolutional neural network (CNN) deep learning model can accurately segment acute ischemic changes on non-contrast CT compared to neuroradiologists. Non-contras…
USE-Evaluator: Performance Metrics for Medical Image Segmentation Models with Uncertain, Small or Empty Reference Annotations
Sophie Ostmeier, Brian Axelrod, Jeroen Bertels +6
Performance metrics for medical image segmentation models are used to measure the agreement between the reference annotation and the predicted segmentation. Usually, overlap metric…
On the Statistical Complexity of Sample Amplification
Brian Axelrod, Shivam Garg, Yanjun Han +2
The ``sample amplification'' problem formalizes the following question: Given i.i.d. samples drawn from an unknown distribution , when is it possible to produce a larger set…
Causal Strategic Linear Regression
Yonadav Shavit, Benjamin Edelman, Brian Axelrod
In many predictive decision-making scenarios, such as credit scoring and academic testing, a decision-maker must construct a model that accounts for agents' propensity to "game" th…
Near-optimal Approximate Discrete and Continuous Submodular Function Minimization
Brian Axelrod, Yang P. Liu, Aaron Sidford
In this paper we provide improved running times and oracle complexities for approximately minimizing a submodular function. Our main result is a randomized algorithm, which given a…
A Polynomial Time Algorithm for Log-Concave Maximum Likelihood via Locally Exponential Families
Brian Axelrod, Ilias Diakonikolas, Anastasios Sidiropoulos +2
We consider the problem of computing the maximum likelihood multivariate log-concave distribution for a set of points. Specifically, we present an algorithm which, given points…
Sample Amplification: Increasing Dataset Size even when Learning is Impossible
Brian Axelrod, Shivam Garg, Vatsal Sharan +1
Given data drawn from an unknown distribution, , to what extent is it possible to ``amplify'' this dataset and output an even larger set of samples that appear to have been draw…
An Efficient Algorithm for High-Dimensional Log-Concave Maximum Likelihood
Brian Axelrod, Gregory Valiant
The log-concave maximum likelihood estimator (MLE) problem answers: for a set of points , which log-concave density maximizes their likelihood? We prese…
Provably Safe Robot Navigation with Obstacle Uncertainty
Brian Axelrod, Leslie Pack Kaelbling, Tomás Lozano-Pérez
As drones and autonomous cars become more widespread it is becoming increasingly important that robots can operate safely under realistic conditions. The noisy information fed into…