7 papers
XConv: Low-memory stochastic backpropagation for convolutional layers
Anirudh Thatipelli, Jeffrey Sam, Mathias Louboutin +3
Training convolutional neural networks at scale demands substantial memory, largely because intermediate activations must be stored for backpropagation. Existing remedies (checkpoi…
Conditional neural control variates for variance reduction in Bayesian inverse problems
Ali Siahkoohi, Hyunwoo Oh
Bayesian inference for inverse problems involves computing expectations under posterior distributions--e.g., posterior means, variances, or predictive quantities--typically via Mon…
Amortized mean-shift interacting particles
Ali Siahkoohi
Bayesian inference for inverse problems is run to evaluate integrals -- posterior expectations, tail probabilities, and risks -- across a stream of observations. The standard estim…
Scalable Bayesian full waveform inversion via dual augmented Lagrangian SVGD
Kamal Aghazade, Ali Siahkoohi, Ali Gholami
Full waveform inversion is an ill-posed inverse problem whose solution non-uniqueness -- i.e., arising from band-limited, finite-aperture, noisy data -- calls for uncertainty quant…
On the role of memorization in learned priors for geophysical inverse problems
Ali Siahkoohi, Davide Sabeddu
Learned priors based on deep generative models offer data-driven regularization for seismic inversion, but training them requires a dataset of representative subsurface models -- a…
Dual-space posterior sampling for Bayesian inference in constrained inverse problems
Ali Siahkoohi, Kamal Aghazade, Ali Gholami
Inverse problems constrained by partial differential equations are often ill-conditioned due to noisy, incomplete data or inherent non-uniqueness. A prominent example is full wavef…