223 citations · 556 across the 23 of their papers we have counts for
24 papers
Vendi Information Gain for Active Learning and its Application to Ecology
Quan Nguyen, Adji Bousso Dieng
While monitoring biodiversity through camera traps has become an important endeavor for ecological research, identifying species in the captured image data remains a major bottlene…
Alternators With Noise Models
Mohammad R. Rezaei, Adji Bousso Dieng
Alternators have recently been introduced as a framework for modeling time-dependent data. They often outperform other popular frameworks, such as state-space models and diffusion…
Vendi Information Gain: An Alternative To Mutual Information For Science And Machine Learning
Quan Nguyen, Adji Bousso Dieng
In his 1948 seminal paper A Mathematical Theory of Communication that birthed information theory, Claude Shannon introduced mutual information (MI), which he called "rate of transm…
The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance
Mohammad Reza Rezaei, Adji Bousso Dieng
Current state-of-the-art dynamical models, such as Mamba, assume the same level of noisiness for all elements of a given sequence, which limits their performance on noisy temporal…
Beyond Aesthetics: Cultural Competence in Text-to-Image Models
Nithish Kannen, Arif Ahmad, Marco Andreetto +5
Text-to-Image (T2I) models are being increasingly adopted in diverse global communities where they create visual representations of their unique cultures. Current T2I benchmarks pr…
Constraint-Aware Diffusion Models for Trajectory Optimization
Anjian Li, Zihan Ding, Adji Bousso Dieng +1
The diffusion model has shown success in generating high-quality and diverse solutions to trajectory optimization problems. However, diffusion models with neural networks inevitabl…
Behavior-Inspired Neural Networks for Relational Inference
Yulong Yang, Bowen Feng, Keqin Wang +3
From pedestrians to Kuramoto oscillators, interactions between agents govern how dynamical systems evolve in space and time. Discovering how these agents relate to each other has t…
Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design
Quan Nguyen, Adji Bousso Dieng
Experimental design techniques such as active search and Bayesian optimization are widely used in the natural sciences for data collection and discovery. However, existing techniqu…
Alternators For Sequence Modeling
Mohammad Reza Rezaei, Adji Bousso Dieng
This paper introduces alternators, a novel family of non-Markovian dynamical models for sequences. An alternator features two neural networks: the observation trajectory network (O…
DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimization
Anjian Li, Zihan Ding, Adji Bousso Dieng +1
Optimal trajectory design is computationally expensive for nonlinear and high-dimensional dynamical systems. The challenge arises from the non-convex nature of the optimization pro…
DMLR: Data-centric Machine Learning Research -- Past, Present and Future
Luis Oala, Manil Maskey, Lilith Bat-Leah +35
Drawing from discussions at the inaugural DMLR workshop at ICML 2023 and meetings prior, in this report we outline the relevance of community engagement and infrastructure developm…
Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning
Amey P. Pasarkar, Adji Bousso Dieng
Measuring diversity accurately is important for many scientific fields, including machine learning (ML), ecology, and chemistry. The Vendi Score was introduced as a generic similar…
The Vendi Score: A Diversity Evaluation Metric for Machine Learning
Dan Friedman, Adji Bousso Dieng
Diversity is an important criterion for many areas of machine learning (ML), including generative modeling and dataset curation. However, existing metrics for measuring diversity a…
Consistency Regularization for Variational Auto-Encoders
Samarth Sinha, Adji B. Dieng
Variational auto-encoders (VAEs) are a powerful approach to unsupervised learning. They enable scalable approximate posterior inference in latent-variable models using variational…
Deep Probabilistic Graphical Modeling
Adji B. Dieng
Probabilistic graphical modeling (PGM) provides a framework for formulating an interpretable generative process of data and expressing uncertainty about unknowns, but it lacks flex…
Prescribed Generative Adversarial Networks
Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei +1
Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limi…
Topic Modeling in Embedding Spaces
Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei
Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed…
The Dynamic Embedded Topic Model
Adji B. Dieng, Francisco J. R. Ruiz, David M. Blei
Topic modeling analyzes documents to learn meaningful patterns of words. For documents collected in sequence, dynamic topic models capture how these patterns vary over time. We dev…
Reweighted Expectation Maximization
Adji B. Dieng, John Paisley
Training deep generative models with maximum likelihood remains a challenge. The typical workaround is to use variational inference (VI) and maximize a lower bound to the log margi…
Avoiding Latent Variable Collapse With Generative Skip Models
Adji B. Dieng, Yoon Kim, Alexander M. Rush +1
Variational autoencoders learn distributions of high-dimensional data. They model data with a deep latent-variable model and then fit the model by maximizing a lower bound of the l…
Noisin: Unbiased Regularization for Recurrent Neural Networks
Adji B. Dieng, Rajesh Ranganath, Jaan Altosaar +1
Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overf…
Augment and Reduce: Stochastic Inference for Large Categorical Distributions
Francisco J. R. Ruiz, Michalis K. Titsias, Adji B. Dieng +1
Categorical distributions are ubiquitous in machine learning, e.g., in classification, language models, and recommendation systems. However, when the number of possible outcomes is…
TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency
Adji B. Dieng, Chong Wang, Jianfeng Gao +1
In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via…
Edward: A library for probabilistic modeling, inference, and criticism
Dustin Tran, Alp Kucukelbir, Adji B. Dieng +3
Probabilistic modeling is a powerful approach for analyzing empirical information. We describe Edward, a library for probabilistic modeling. Edward's design reflects an iterative p…