Search Results for author:
Found 32 papers, 11 papers with code
Continuous Language Model Interpolation for Dynamic and Controllable Text Generation
We empirically show that varying the interpolation weights yields predictable and consistent change in the model outputs with respect to all of the controlled attributes.
Distributional Dataset Distillation with Subtask Decomposition
What does a neural network learn when training from a task-specific dataset?
Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains
Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language.
Generating Synthetic Datasets by Interpolating along Generalized Geodesics
We compute these geodesics using a recent notion of distance between labeled datasets, and derive alternative interpolation schemes based on it: using either barycentric projections or optimal transport maps, the latter computed using recent neural OT methods.
Domain adaptation using optimal transport for invariant learning using histopathology datasets
Histopathology is critical for the diagnosis of many diseases, including cancer.
Transfer RL via the Undo Maps Formalism
Transferring knowledge across domains is one of the most fundamental problems in machine learning, but doing so effectively in the context of reinforcement learning remains largely an open problem.
Budget-Constrained Bounds for Mini-Batch Estimation of Optimal Transport
Optimal Transport (OT) is a fundamental tool for comparing probability distributions, but its exact computation remains prohibitive for large datasets.
InfoOT: Information Maximizing Optimal Transport
Optimal transport aligns samples across distributions by minimizing the transportation cost between them, e. g., the geometric distances.
Neural Unbalanced Optimal Transport via Cycle-Consistent Semi-Couplings
However, the usual formulation of OT assumes conservation of mass, which is violated in unbalanced scenarios in which the population size changes (e. g., cell proliferation or death) between measurements.
Interpretable Distribution Shift Detection using Optimal Transport
We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport.
Why GANs are overkill for NLP
We show that, while it may seem that maximizing likelihood is inherently different than minimizing distinguishability, this distinction is largely artificial and only holds for limited models.
Hierarchical Optimal Transport for Comparing Histopathology Datasets
Scarcity of labeled histopathology data limits the applicability of deep learning methods to under-profiled cancer types and labels.
Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks
Gradient flows are a powerful tool for optimizing functionals in general metric spaces, including the space of probabilities endowed with the Wasserstein metric.
From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence
We take inspiration from the study of human explanation to inform the design and evaluation of interpretability methods in machine learning.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
Dataset Dynamics via Gradient Flows in Probability Space
Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation.
Geometric Dataset Distances via Optimal Transport
The notion of task similarity is at the core of various machine learning paradigms, such as domain adaptation and meta-learning.
Unsupervised Hierarchy Matching with Optimal Transport over Hyperbolic Spaces
This paper focuses on the problem of unsupervised alignment of hierarchical data such as ontologies or lexical databases.
Probabilistic Bias Mitigation in Word Embeddings
In this work we propose a probabilistic view of word embedding bias.
Weight of Evidence as a Basis for Human-Oriented Explanations
Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods.
Towards Robust, Locally Linear Deep Networks
In this paper, we propose a new learning problem to encourage deep networks to have stable derivatives over larger regions.
Learning Generative Models across Incomparable Spaces
Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety.
Functional Transparency for Structured Data: a Game-Theoretic Approach
We provide a new approach to training neural models to exhibit transparency in a well-defined, functional manner.
Gromov-Wasserstein Alignment of Word Embedding Spaces
Cross-lingual or cross-domain correspondences play key roles in tasks ranging from machine translation to transfer learning.
Game-Theoretic Interpretability for Temporal Modeling
In contrast, we focus on temporal modeling and the problem of tailoring the predictor, functionally, towards an interpretable family.
Towards Optimal Transport with Global Invariances
Many problems in machine learning involve calculating correspondences between sets of objects, such as point clouds or images.
On the Robustness of Interpretability Methods
We argue that robustness of explanations---i. e., that similar inputs should give rise to similar explanations---is a key desideratum for interpretability.
Towards Robust Interpretability with Self-Explaining Neural Networks
Most recent work on interpretability of complex machine learning models has focused on estimating $\textit{a posteriori}$ explanations for previously trained models around specific predictions.
Structured Optimal Transport
Optimal Transport has recently gained interest in machine learning for applications ranging from domain adaptation, sentence similarities to deep learning.
A causal framework for explaining the predictions of black-box sequence-to-sequence models
We interpret the predictions of any black-box structured input-structured output model around a specific input-output pair.
Distributional Adversarial Networks
We propose a framework for adversarial training that relies on a sample rather than a single sample point as the fundamental unit of discrimination.
Word Embeddings as Metric Recovery in Semantic Spaces
Continuous word representations have been remarkably useful across NLP tasks but remain poorly understood.
Word, graph and manifold embedding from Markov processes
Continuous vector representations of words and objects appear to carry surprisingly rich semantic content.
