7 papers
Amortized Factor Inference Networks for Posterior Inference
Joohwan Ko, Justin Domke
Amortized inference promises fast test-time Bayesian inference, but existing methods are inherently tied to fixed models. Extending amortization to unseen models typically requires…
Latent Target Score Matching, with an application to Simulation-Based Inference
Joohwan Ko, Tomas Geffner
Denoising score matching (DSM) for training diffusion models may suffer from high variance at low noise levels. Target Score Matching (TSM) mitigates this when clean data scores ar…
Provably Scalable Black-Box Variational Inference with Structured Variational Families
Joohwan Ko, Kyurae Kim, Woo Chang Kim +1
Variational families with full-rank covariance approximations are known not to work well in black-box variational inference (BBVI), both empirically and theoretically. In fact, rec…
Model-Informed Flows for Bayesian Inference
Joohwan Ko, Justin Domke
Variational inference often struggles with the posterior geometry exhibited by complex hierarchical Bayesian models. Recent advances in flow-based variational families and Variatio…
Relaxed Sequence Sampling for Diverse Protein Design
Joohwan Ko, Aristofanis Rontogiannis, Yih-En Andrew Ban +2
Protein design using structure prediction models such as AlphaFold2 has shown remarkable success, but existing approaches like relaxed sequence optimization (RSO) rely on single-pa…
Demystifying SGD with Doubly Stochastic Gradients
Kyurae Kim, Joohwan Ko, Yi-An Ma +1
Optimization objectives in the form of a sum of intractable expectations are rising in importance (e.g., diffusion models, variational autoencoders, and many more), a setting also…