Publications in Machine Learning Venues
ICML
Connectivity-Optimized Representation Learning via Persistent HomologyConnectivity-Optimized Representation Learning via Persistent Homology
We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the …
Dissecting Supervised Constrastive Learning
Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular …
Graph Filtration Learning
We propose an approach to learning with graph-structured data in the problem domain of graph classification. In particular, we present …
Topologically Densified Distributions
We study regularization in the context of small sample-size learning with over-parameterized neural networks. Specifically, we shift …
NeurIPS
A shooting formulation of deep learningA shooting formulation of deep learning
Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of …
Accurate Point Cloud Registration with Robust Optimal Transport
This work investigates the use of robust optimal transport (OT) for shape matching. Specifically, we show that recent OT solvers …
Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language
Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of …
Deep Learning with Topological Signatures
Inferring topological and geometrical information from data can offer an alternative perspective in machine learning problems. Methods …
On Measuring Excess Capacity in Neural Networks
We study the excess capacity of deep networks in the context of supervised classification. That is, given a capacity measure of the …
Region-specific Diffeomorphic Metric Mapping
We introduce a region-specific diffeomorphic metric mapping (RDMM) registration approach. RDMM is non-parametric, estimating …
Statistical Topological Data Analysis - A Kernel Perspective
We consider the problem of statistical computations with persistence diagrams, a summary representation of topological features in …
AAAI
Deep Message Passing on SetsDeep Message Passing on Sets
Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a …
AISTATS
Regression Uncertainty on the GrassmannianRegression Uncertainty on the Grassmannian
Trends in longitudinal or cross-sectional studies over time are often captured through regression models. In their simplest …
JMLR
Learning Representations of Persistence Barcodes