9 citations · 24 across the 16 of their papers we have counts for
19 papers
Inverted Detection and Control in Steering Vectors
Max Torop, Aria Masoomi, Jennifer Dy
Steering vectors (SVs) are widely used to influence the expression of concepts (e.g., truthfulness) in large language model outputs. A key assumption underpinning SVs is that they…
Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
Aria Masoomi, Mahsa Bazzaz, Adel Javanmard +1
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to solve complex problems by generating intermediate reasoning steps. While much attention has been paid to th…
DISCO: Disentangled Communication Steering for Large Language Models
Max Torop, Aria Masoomi, Masih Eskandar +1
A variety of recent methods guide large language model outputs via the inference-time addition of steering vectors to residual-stream or attention-head representations. In contrast…
OrdShap: Feature Position Importance for Sequential Black-Box Models
Davin Hill, Brian L. Hill, Aria Masoomi +3
Sequential deep learning models excel in domains with temporal or sequential dependencies, but their complexity necessitates post-hoc feature attribution methods for understanding…
Axiomatic Explainer Globalness via Optimal Transport
Davin Hill, Josh Bone, Aria Masoomi +2
Explainability methods are often challenging to evaluate and compare. With a multitude of explainers available, practitioners must often compare and select explainers based on quan…
The Poisson degeneracy locus of a flag variety
Élie Casbi, Aria Masoomi, Milen Yakimov
We present a comprehensive study of the degeneracy loci of the full flag varieties of all complex semisimple Lie groups equipped with the standard Poisson structures. The reduced P…
SmoothHess: ReLU Network Feature Interactions via Stein's Lemma
Max Torop, Aria Masoomi, Davin Hill +3
Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-…
Explanations of Black-Box Models based on Directional Feature Interactions
Aria Masoomi, Davin Hill, Zhonghui Xu +5
As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain bl…
Geometry of Score Based Generative Models
Sandesh Ghimire, Jinyang Liu, Armand Comas +4
In this work, we look at Score-based generative models (also called diffusion generative models) from a geometric perspective. From a new view point, we prove that both the forward…
Divide and Compose with Score Based Generative Models
Sandesh Ghimire, Armand Comas, Davin Hill +3
While score based generative models, or diffusion models, have found success in image synthesis, they are often coupled with text data or image label to be able to manipulate and c…
Boundary-Aware Uncertainty for Feature Attribution Explainers
Davin Hill, Aria Masoomi, Max Torop +2
Post-hoc explanation methods have become a critical tool for understanding black-box classifiers in high-stakes applications. However, high-performing classifiers are often highly…
Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions
Zulqarnain Khan, Davin Hill, Aria Masoomi +2
Machine learning methods have significantly improved in their predictive capabilities, but at the same time they are becoming more complex and less transparent. As a result, explai…
Deep Layer-wise Networks Have Closed-Form Weights
Chieh Wu, Aria Masoomi, Arthur Gretton +1
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP). To better mimic the brain, training a network \texti…
Reliable Estimation of KL Divergence using a Discriminator in Reproducing Kernel Hilbert Space
Sandesh Ghimire, Aria Masoomi, Jennifer Dy
Estimating Kullback Leibler (KL) divergence from samples of two distributions is essential in many machine learning problems. Variational methods using neural network discriminator…
Deep Bayesian Unsupervised Lifelong Learning
Tingting Zhao, Zifeng Wang, Aria Masoomi +1
Lifelong Learning (LL) refers to the ability to continually learn and solve new problems with incremental available information over time while retaining previous knowledge. Much a…
Revisiting Hilbert-Schmidt Information Bottleneck for Adversarial Robustness
Zifeng Wang, Tong Jian, Aria Masoomi +2
We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. In addition to the…
Kernel Dependence Network
Chieh Wu, Aria Masoomi, Arthur Gretton +1
We propose a greedy strategy to spectrally train a deep network for multi-class classification. Each layer is defined as a composition of linear weights with the feature map of a G…
Deep Layer-wise Networks Have Closed-Form Weights
Chieh Wu, Aria Masoomi, Arthur Gretton +1
There is currently a debate within the neuroscience community over the likelihood of the brain performing backpropagation (BP). To better mimic the brain, training a network $\text…
Streaming Adaptive Nonparametric Variational Autoencoder
Tingting Zhao, Zifeng Wang, Aria Masoomi +1
We develop a data driven approach to perform clustering and end-to-end feature learning simultaneously for streaming data that can adaptively detect novel clusters in emerging data…