Search Results for author:
Found 15 papers, 11 papers with code
Listening to the Noise: Blind Denoising with Gibbs Diffusion
Assuming arbitrary parametric Gaussian noise, we develop a Gibbs algorithm that alternates sampling steps from a conditional diffusion model trained to map the signal prior to the family of noise distributions, and a Monte Carlo sampler to infer the noise parameters.
Removing Dust from CMB Observations with Diffusion Models
We investigate diffusion-based modeling of the dust foreground and its interest for component separation.
AstroCLIP: Cross-Modal Pre-Training for Astronomical Foundation Models
We present AstroCLIP, a strategy to facilitate the construction of astronomical foundation models that bridge the gap between diverse observational modalities.
Multiple Physics Pretraining for Physical Surrogate Models
We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling.
xVal: A Continuous Number Encoding for Large Language Models
Large Language Models have not yet been broadly adapted for the analysis of scientific datasets due in part to the unique difficulties of tokenizing numbers.
MoMo: Momentum Models for Adaptive Learning Rates
MoMo uses momentum estimates of the batch losses and gradients sampled at each iteration to build a model of the loss function.
Shedding a PAC-Bayesian Light on Adaptive Sliced-Wasserstein Distances
The Sliced-Wasserstein distance (SW) is a computationally efficient and theoretically grounded alternative to the Wasserstein distance.
Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel
Commonly used approaches avoid computing the high-dimensional tensor product explicitly, resulting in a suboptimal dependence of $\mathcal{O}(3^p)$ in the embedding dimension.
ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients
Robustness to adversarial attacks is typically obtained through expensive adversarial training with Projected Gradient Descent.
Photonic Differential Privacy with Direct Feedback Alignment
Optical Processing Units (OPUs) -- low-power photonic chips dedicated to large scale random projections -- have been used in previous work to train deep neural networks using Direct Feedback Alignment (DFA), an effective alternative to backpropagation.
Photonic co-processors in HPC: using LightOn OPUs for Randomized Numerical Linear Algebra
Randomized Numerical Linear Algebra (RandNLA) is a powerful class of methods, widely used in High Performance Computing (HPC).
Adversarial Robustness by Design through Analog Computing and Synthetic Gradients
In the white-box setting, our defense works by obfuscating the parameters of the random projection.
Align, then memorise: the dynamics of learning with feedback alignment
Direct Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to the ubiquitous backpropagation algorithm for training deep neural networks.
Reservoir Computing meets Recurrent Kernels and Structured Transforms
Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained.
Kernel computations from large-scale random features obtained by Optical Processing Units
Approximating kernel functions with random features (RFs)has been a successful application of random projections for nonparametric estimation.
