53 citations · 70 across the 7 of their papers we have counts for
7 papers
BiXSE: Improving Dense Retrieval via Probabilistic Graded Relevance Distillation
Christos Tsirigotis, Vaibhav Adlakha, Joao Monteiro +2
Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world…
FLAM: Frame-Wise Language-Audio Modeling
Yusong Wu, Christos Tsirigotis, Ke Chen +5
Recent multi-modal audio-language models (ALMs) excel at text-audio retrieval but struggle with frame-wise audio understanding. Prior works use temporal-aware labels or unsupervise…
Group Robust Classification Without Any Group Information
Christos Tsirigotis, Joao Monteiro, Pau Rodriguez +2
Empirical risk minimization (ERM) is sensitive to spurious correlations in the training data, which poses a significant risk when deploying systems trained under this paradigm in h…
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
Damien Ferbach, Christos Tsirigotis, Gauthier Gidel +2
The Strong Lottery Ticket Hypothesis (SLTH) stipulates the existence of a subnetwork within a sufficiently overparameterized (dense) neural network that -- when initialized randoml…
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
Samuel Lavoie, Christos Tsirigotis, Max Schwarzer +4
Simplicial Embeddings (SEM) are representations learned through self-supervised learning (SSL), wherein a representation is projected into simplices of dimensions each usin…
Convex Potential Flows: Universal Probability Distributions with Optimal Transport and Convex Optimization
Chin-Wei Huang, Ricky T. Q. Chen, Christos Tsirigotis +1
Flow-based models are powerful tools for designing probabilistic models with tractable density. This paper introduces Convex Potential Flows (CP-Flow), a natural and efficient para…
A Walk with SGD
Chen Xing, Devansh Arpit, Christos Tsirigotis +1
We present novel empirical observations regarding how stochastic gradient descent (SGD) navigates the loss landscape of over-parametrized deep neural networks (DNNs). These observa…