1 citations · 1 across the 7 of their papers we have counts for
11 papers
Discrete Diffusion Models are Minimax Optimal Under Sparsity
Luca Blunda, Tyler Farghly, Umut Simsekli +1
Discrete diffusion models have emerged as a leading alternative to autoregressive models for generating text and other categorical data, yet their theoretical foundations remain le…
Rapid Mixing of Stereographic MCMC for Heavy-Tailed Sampling
Federica Milinanni, Tyler Farghly, Jun Yang
Sampling from high-dimensional, heavy-tailed distributions is a fundamental challenge in computational statistics, as many standard Markov chain Monte Carlo (MCMC) methods mix poor…
Tightening the Score Matching Gap for Diffusion Models
Benjamin Dupuis, Tyler Farghly, Maxime Haddouche +2
Diffusion models (DMs) are a state-of-the-art generative method to approximately sample from an unknown distribution. Their training and evaluation primarily rely on an Evidence Lo…
Benign Overfitting Does Not Occur in Diffusion Models
Tyler Farghly, Benjamin Dupuis, Alain Durmus +1
Benign overfitting and double descent have come to shape our understanding of generalization in deep learning, establishing that overfitting is not only compatible with good genera…
Metropolis-Adjusted Diffusion Models
Kevin H. Lam, Tyler Farghly, Christopher Williams +3
Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to a…
On-Average Stability of Multipass Preconditioned SGD and Effective Dimension
Simon Vary, Tyler Farghly, Ilja Kuzborskij +1
We study trade-offs between the population risk curvature, geometry of the noise, and preconditioning on the generalisation ability of the multipass Preconditioned Stochastic Gradi…
Diffusion Models and the Manifold Hypothesis: Log-Domain Smoothing is Geometry Adaptive
Tyler Farghly, Peter Potaptchik, Samuel Howard +2
Diffusion models have achieved state-of-the-art performance, demonstrating remarkable generalisation capabilities across diverse domains. However, the mechanisms underpinning these…
Beyond Real Data: Synthetic Data through the Lens of Regularization
Amitis Shidani, Tyler Farghly, Yang Sun +2
Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we prese…
Implicit Regularisation in Diffusion Models: An Algorithm-Dependent Generalisation Analysis
Tyler Farghly, Patrick Rebeschini, George Deligiannidis +1
The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown…
Generalisation under gradient descent via deterministic PAC-Bayes
Eugenio Clerico, Tyler Farghly, George Deligiannidis +2
We establish disintegrated PAC-Bayesian generalisation bounds for models trained with gradient descent methods or continuous gradient flows. Contrary to standard practice in the PA…
Time-independent Generalization Bounds for SGLD in Non-convex Settings
Tyler Farghly, Patrick Rebeschini
We establish generalization error bounds for stochastic gradient Langevin dynamics (SGLD) with constant learning rate under the assumptions of dissipativity and smoothness, a setti…