90 citations · 332 across the 63 of their papers we have counts for
9 papers · 1 filter
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias
Frederic Koehler, Viraj Mehta, Chenghui Zhou +1
Variational Autoencoders are one of the most commonly used generative models, particularly for image data. A prominent difficulty in training VAEs is data that is supported on a lo…
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation
Bingbin Liu, Elan Rosenfeld, Pradeep Ravikumar +1
Noise-contrastive estimation (NCE) is a statistically consistent method for learning unnormalized probabilistic models. It has been empirically observed that the choice of the nois…
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders
Divyansh Pareek, Andrej Risteski
Training and using modern neural-network based latent-variable generative models (like Variational Autoencoders) often require simultaneously training a generative direction along…
Universal Approximation for Log-concave Distributions using Well-conditioned Normalizing Flows
Holden Lee, Chirag Pabbaraju, Anish Sevekari +1
Normalizing flows are a widely used class of latent-variable generative models with a tractable likelihood. Affine-coupling (Dinh et al, 2014-16) models are a particularly common t…
The Limitations of Limited Context for Constituency Parsing
Yuchen Li, Andrej Risteski
Incorporating syntax into neural approaches in NLP has a multitude of practical and scientific benefits. For instance, a language model that is syntax-aware is likely to be able to…
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
Yining Chen, Elan Rosenfeld, Mark Sellke +2
Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments. Despite a proliferation of proposal algorithms f…
Contrastive learning of strong-mixing continuous-time stochastic processes
Bingbin Liu, Pradeep Ravikumar, Andrej Risteski
Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one…
Parametric Complexity Bounds for Approximating PDEs with Neural Networks
Tanya Marwah, Zachary C. Lipton, Andrej Risteski
Recent experiments have shown that deep networks can approximate solutions to high-dimensional PDEs, seemingly escaping the curse of dimensionality. However, questions regarding th…
An Online Learning Approach to Interpolation and Extrapolation in Domain Generalization
Elan Rosenfeld, Pradeep Ravikumar, Andrej Risteski
A popular assumption for out-of-distribution generalization is that the training data comprises sub-datasets, each drawn from a distinct distribution; the goal is then to "interpol…