Search Results for author:
Found 26 papers, 11 papers with code
Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding
Deep Bayesian latent variable models have enabled new approaches to both model and data compression.
Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector
We revisit the likelihood ratio between a pretrained large language model (LLM) and its finetuned variant as a criterion for out-of-distribution (OOD) detection.
Predictive, scalable and interpretable knowledge tracing on structured domains
This requires estimates of both the learner's progress (''knowledge tracing''; KT), and the prerequisite structure of the learning domain (''knowledge mapping'').
On the Challenges and Opportunities in Generative AI
The field of deep generative modeling has grown rapidly and consistently over the years.
A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry
Bayesian neural networks (BNNs) are a principled approach to modeling predictive uncertainties in deep learning, which are important in safety-critical applications.
Upgrading VAE Training With Unlimited Data Plans Provided by Diffusion Models
Variational autoencoders (VAEs) are popular models for representation learning but their encoders are susceptible to overfitting (Cremer et al., 2018) because they are trained on a finite training set instead of the true (continuous) data distribution $p_{\mathrm{data}}(\mathbf{x})$.
The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch
However, with this work, we aim to warn the community about an issue of the SVHN dataset as a benchmark for generative modeling tasks: we discover that the official split into training set and test set of the SVHN dataset are not drawn from the same distribution.
Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers
Annealed Importance Sampling (AIS) moves particles along a Markov chain from a tractable initial distribution to an intractable target distribution.
Trading Information between Latents in Hierarchical Variational Autoencoders
Variational Autoencoders (VAEs) were originally motivated (Kingma & Welling, 2014) as probabilistic generative models in which one performs approximate Bayesian inference.
Hybridizing Physical and Data-driven Prediction Methods for Physicochemical Properties
We apply the new approach to predict activity coefficients at infinite dilution and obtain significant improvements compared to the data-driven and physical baselines and established ensemble methods from the machine learning literature.
Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspective
Entropy coding is the backbone data compression.
User-Dependent Neural Sequence Models for Continuous-Time Event Data
Modeling such data can be very challenging, in particular for applications with many different types of events, since it requires a model to predict the event types as well as the time of occurrence.
Improving Inference for Neural Image Compression
We consider the problem of lossy image compression with deep latent variable models.
Variational Bayesian Quantization
Our experimental results demonstrate the importance of taking into account posterior uncertainties, and show that image compression with the proposed algorithm outperforms JPEG over a wide range of bit rates using only a single standard VAE.
Extreme Classification via Adversarial Softmax Approximation
Training a classifier over a large number of classes, known as 'extreme classification', has become a topic of major interest with applications in technology, science, and e-commerce.
Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion
Activity coefficients, which are a measure of the non-ideality of liquid mixtures, are a key property in chemical engineering with relevance to modeling chemical and phase equilibria as well as transport processes.
Tightening Bounds for Variational Inference by Revisiting Perturbation Theory
In this paper, we revisit perturbation theory as a powerful way of improving the variational approximation.
A Quantum Field Theory of Representation Learning
Continuous symmetries and their breaking play a prominent role in contemporary physics.
Augmenting and Tuning Knowledge Graph Embeddings
Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i. e., the task of completing an incomplete collection of relational facts.
Ranked #5 on
Link Prediction
on FB15k
Probabilistic Knowledge Graph Embeddings
We develop a probabilistic extension of state-of-the-art embedding models for link prediction in relational knowledge graphs.
Improving Optimization in Models With Continuous Symmetry Breaking
We show that representation learning models for time series possess an approximate continuous symmetry that leads to slow convergence of gradient descent.
Improving Optimization for Models With Continuous Symmetry Breaking
We show that representation learning models for time series possess an approximate continuous symmetry that leads to slow convergence of gradient descent.
Bayesian Paragraph Vectors
Word2vec (Mikolov et al., 2013) has proven to be successful in natural language processing by capturing the semantic relationships between different words.
Perturbative Black Box Variational Inference
Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as alpha divergences.
Structured Black Box Variational Inference for Latent Time Series Models
Black box variational inference with reparameterization gradients (BBVI) allows us to explore a rich new class of Bayesian non-conjugate latent time series models; however, a naive application of BBVI to such structured variational models would scale quadratically in the number of time steps.
Dynamic Word Embeddings
We present a probabilistic language model for time-stamped text data which tracks the semantic evolution of individual words over time.
