Fred Roosta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Fred Roosta has a total of 56 co-authors. Here are the top co-authors by number of shared publications:
- Michael W. Mahoney
Department of Statistics ICSI LBNL University of California at Berkeley
8 shared publications Michael W. Mahoney
5 shared publicationsPeng Xu
Amazon AWS AI (Work done while at the Institute for Computational and Mathematical Engineering , Stanford University, Stanford, CA 94305, USA)
5 shared publications- Liam Hodgkinson
ICSI Department of Statistics University of California Berkeley
3 shared publications - Marcus Gallagher
University of Queensland
3 shared publications - Ali Eshragh
School of Information and Physical Sciences University of Newcastle NSW Australia
2 shared publications
Latest Publications
- Open Access
Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to data, thereby enhancing efficiency in both training and inference. However, current flow-based inverse solvers face two primary limitations: (i) they operate directly in pixel space, which demands heavy computational resources for training and restricts scalability to high-resolution images, and (ii) they employ guidance strategies with prior-agnostic posterior covariances, which can weaken alignment with the generative trajectory and degrade posterior coverage. In this paper, we propose LFlow (Latent Refinement via Flows), a training-free framework for solving linear inverse problems via pretrained latent flow priors. LFlow leverages the efficiency of flow matching to perform ODE sampling in latent space along an optimal path. This latent formulation further allows us to introduce a theoretically grounded posterior covariance, derived from the optimal vector field, enabling effective flow guidance. Experimental results demonstrate that our proposed method outperforms state-of-the-art latent diffusion solvers in reconstruction quality across most tasks. The code will be publicly available at https://github.com/hosseinaskari-cs/LFlow .
Open AccessLatent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to data, thereby enhancing efficiency in both training and inference. However, current flow-based inverse solvers face two primary limitations: (i) they operate directly in pixel space, which demands heavy computational resources for training and restricts scalability to high-resolution images, and (ii) they employ guidance strategies with prior-agnostic posterior covariances, which can weaken alignment with the generative trajectory and degrade posterior coverage. In this paper, we propose LFlow (Latent Refinement via Flows), a training-free framework for solving linear inverse problems via pretrained latent flow priors. LFlow leverages the efficiency of flow matching to perform ODE sampling in latent space along an optimal path. This latent formulation further allows us to introduce a theoretically grounded posterior covariance, derived from the optimal vector field, enabling effective flow guidance. Experimental results demonstrate that our proposed method outperforms state-of-the-art latent diffusion solvers in reconstruction quality across most tasks. The code will be publicly available at https://github.com/hosseinaskari-cs/LFlow .
- 7 August 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Matrix Analysis and Applications
- Vol. 46 (3) , 1887-1916
Obtaining Pseudoinverse Solutions with MINRES
The celebrated minimum residual method (MINRES), proposed in the seminal paper of Paige and Saunders [ SIAM J. Numer. Anal., 12 (1975), pp. 617–62951], has seen great success and widespread use in solving Hermitian (and complex-symmetric) systems [Formula: see text]. Unless the system is consistent, MINRES is not guaranteed to obtain the pseudoinverse solution. We propose a novel and remarkably simple minimum-norm (MN) refinement that seamlessly integrates with the final MINRES iteration, enabling us to obtain the minimum-norm solution with negligible additional computational cost. We extend our MN refinement to complex-symmetric systems, building on S.-C. Choi’s extension of MINRES for solving these systems. Given the flexibility of MINRES to accommodate singular preconditioners, we further investigate the MN refinement in preconditioned settings that involve singular preconditioners. We also provide numerical experiments to support our analysis and showcase the effects of our MN refinement.
- 7 August 2025
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Matrix Analysis and Applications
- Vol. 46 (3) , 1887-1916
Obtaining Pseudoinverse Solutions with MINRES
The celebrated minimum residual method (MINRES), proposed in the seminal paper of Paige and Saunders [ SIAM J. Numer. Anal., 12 (1975), pp. 617–62951], has seen great success and widespread use in solving Hermitian (and complex-symmetric) systems [Formula: see text]. Unless the system is consistent, MINRES is not guaranteed to obtain the pseudoinverse solution. We propose a novel and remarkably simple minimum-norm (MN) refinement that seamlessly integrates with the final MINRES iteration, enabling us to obtain the minimum-norm solution with negligible additional computational cost. We extend our MN refinement to complex-symmetric systems, building on S.-C. Choi’s extension of MINRES for solving these systems. Given the flexibility of MINRES to accommodate singular preconditioners, we further investigate the MN refinement in preconditioned settings that involve singular preconditioners. We also provide numerical experiments to support our analysis and showcase the effects of our MN refinement.
- Open Access
Importance Sampling for Nonlinear Models
While norm-based and leverage-score-based methods have been extensively studied for identifying "important" data points in linear models, analogous tools for nonlinear models remain significantly underdeveloped. By introducing the concept of the adjoint operator of a nonlinear map, we address this gap and generalize norm-based and leverage-score-based importance sampling to nonlinear settings. We demonstrate that sampling based on these generalized notions of norm and leverage scores provides approximation guarantees for the underlying nonlinear mapping, similar to linear subspace embeddings. As direct applications, these nonlinear scores not only reduce the computational complexity of training nonlinear models by enabling efficient sampling over large datasets but also offer a novel mechanism for model explainability and outlier detection. Our contributions are supported by both theoretical analyses and experimental results across a variety of supervised learning scenarios.
Open AccessImportance Sampling for Nonlinear Models
While norm-based and leverage-score-based methods have been extensively studied for identifying "important" data points in linear models, analogous tools for nonlinear models remain significantly underdeveloped. By introducing the concept of the adjoint operator of a nonlinear map, we address this gap and generalize norm-based and leverage-score-based importance sampling to nonlinear settings. We demonstrate that sampling based on these generalized notions of norm and leverage scores provides approximation guarantees for the underlying nonlinear mapping, similar to linear subspace embeddings. As direct applications, these nonlinear scores not only reduce the computational complexity of training nonlinear models by enabling efficient sampling over large datasets but also offer a novel mechanism for model explainability and outlier detection. Our contributions are supported by both theoretical analyses and experimental results across a variety of supervised learning scenarios.
- Open Access
SALSA: Sequential Approximate Leverage-Score Algorithm with Application in Analyzing Big Time Series Data
We develop a new efficient sequential approximate leverage score algorithm, SALSA, using methods from randomized numerical linear algebra (RandNLA) for large matrices. We demonstrate that, with high probability, the accuracy of SALSA's approximations is within $(1 + O({\varepsilon}))$ of the true leverage scores. In addition, we show that the theoretical computational complexity and numerical accuracy of SALSA surpass existing approximations. These theoretical results are subsequently utilized to develop an efficient algorithm, named LSARMA, for fitting an appropriate ARMA model to large-scale time series data. Our proposed algorithm is, with high probability, guaranteed to find the maximum likelihood estimates of the parameters for the true underlying ARMA model. Furthermore, it has a worst-case running time that significantly improves those of the state-of-the-art alternatives in big data regimes. Empirical results on large-scale data strongly support these theoretical results and underscore the efficacy of our new approach.Open AccessSALSA: Sequential Approximate Leverage-Score Algorithm with Application in Analyzing Big Time Series Data
We develop a new efficient sequential approximate leverage score algorithm, SALSA, using methods from randomized numerical linear algebra (RandNLA) for large matrices. We demonstrate that, with high probability, the accuracy of SALSA's approximations is within $(1 + O({\varepsilon}))$ of the true leverage scores. In addition, we show that the theoretical computational complexity and numerical accuracy of SALSA surpass existing approximations. These theoretical results are subsequently utilized to develop an efficient algorithm, named LSARMA, for fitting an appropriate ARMA model to large-scale time series data. Our proposed algorithm is, with high probability, guaranteed to find the maximum likelihood estimates of the parameters for the true underlying ARMA model. Furthermore, it has a worst-case running time that significantly improves those of the state-of-the-art alternatives in big data regimes. Empirical results on large-scale data strongly support these theoretical results and underscore the efficacy of our new approach. - Open Access
Non-Uniform Smoothness for Gradient Descent
The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given problem. In this work we introduce a local first-order smoothness oracle (LFSO) which generalizes the Lipschitz continuous gradients smoothness condition and is applicable to any twice-differentiable function. We show that this oracle can encode all relevant problem information for tuning stepsizes for a suitably modified gradient descent method and give global and local convergence results. We also show that LFSOs in this modified first-order method can yield global linear convergence rates for non-strongly convex problems with extremely flat minima, and thus improve over the lower bound on rates achievable by general (accelerated) first-order methods.
Open AccessNon-Uniform Smoothness for Gradient Descent
The analysis of gradient descent-type methods typically relies on the Lipschitz continuity of the objective gradient. This generally requires an expensive hyperparameter tuning process to appropriately calibrate a stepsize for a given problem. In this work we introduce a local first-order smoothness oracle (LFSO) which generalizes the Lipschitz continuous gradients smoothness condition and is applicable to any twice-differentiable function. We show that this oracle can encode all relevant problem information for tuning stepsizes for a suitably modified gradient descent method and give global and local convergence results. We also show that LFSOs in this modified first-order method can yield global linear convergence rates for non-strongly convex problems with extremely flat minima, and thus improve over the lower bound on rates achievable by general (accelerated) first-order methods.
- Open Access
A PAC-Bayesian Perspective on the Interpolating Information Criterion
Deep learning is renowned for its theory-practice gap, whereby principled theory typically fails to provide much beneficial guidance for implementation in practice. This has been highlighted recently by the benign overfitting phenomenon: when neural networks become sufficiently large to interpolate the dataset perfectly, model performance appears to improve with increasing model size, in apparent contradiction with the well-known bias-variance tradeoff. While such phenomena have proven challenging to theoretically study for general models, the recently proposed Interpolating Information Criterion (IIC) provides a valuable theoretical framework to examine performance for overparameterized models. Using the IIC, a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence generalization performance in the interpolating regime. From the provided bound, we quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, optimizer, and parameter-initialization scheme; the spectrum of the empirical neural tangent kernel; curvature of the loss landscape; and noise present in the data.
Open AccessA PAC-Bayesian Perspective on the Interpolating Information Criterion
Deep learning is renowned for its theory-practice gap, whereby principled theory typically fails to provide much beneficial guidance for implementation in practice. This has been highlighted recently by the benign overfitting phenomenon: when neural networks become sufficiently large to interpolate the dataset perfectly, model performance appears to improve with increasing model size, in apparent contradiction with the well-known bias-variance tradeoff. While such phenomena have proven challenging to theoretically study for general models, the recently proposed Interpolating Information Criterion (IIC) provides a valuable theoretical framework to examine performance for overparameterized models. Using the IIC, a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence generalization performance in the interpolating regime. From the provided bound, we quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, optimizer, and parameter-initialization scheme; the spectrum of the empirical neural tangent kernel; curvature of the loss landscape; and noise present in the data.
- Open Access
A Newton-MR algorithm with complexity guarantees for nonconvex smooth unconstrained optimization
In this paper, we consider variants of Newton-MR algorithm for solving unconstrained, smooth, but non-convex optimization problems. Unlike the overwhelming majority of Newton-type methods, which rely on conjugate gradient algorithm as the primary workhorse for their respective sub-problems, Newton-MR employs minimum residual (MINRES) method. Recently, it has been established that MINRES has inherent ability to detect non-positive curvature directions as soon as they arise and certain useful monotonicity properties will be satisfied before such detection. We leverage these recent results and show that our algorithms come with desirable properties including competitive first and second-order worst-case complexities. Numerical examples demonstrate the performance of our proposed algorithms.
Open AccessA Newton-MR algorithm with complexity guarantees for nonconvex smooth unconstrained optimization
In this paper, we consider variants of Newton-MR algorithm for solving unconstrained, smooth, but non-convex optimization problems. Unlike the overwhelming majority of Newton-type methods, which rely on conjugate gradient algorithm as the primary workhorse for their respective sub-problems, Newton-MR employs minimum residual (MINRES) method. Recently, it has been established that MINRES has inherent ability to detect non-positive curvature directions as soon as they arise and certain useful monotonicity properties will be satisfied before such detection. We leverage these recent results and show that our algorithms come with desirable properties including competitive first and second-order worst-case complexities. Numerical examples demonstrate the performance of our proposed algorithms.
- 22 August 2022
- Published by Oxford University Press (OUP) in IMA Journal of Numerical Analysis
- Vol. 43 (3) , 1855-1897
Inexact Newton-CG algorithms with complexity guarantees
We consider variants of a recently developed Newton-CG algorithm for nonconvex problems (Royer, C. W. & Wright, S. J. (2018) Complexity analysis of second-order line-search algorithms for smooth nonconvex optimization. SIAM J. Optim., 28, 1448–1477) in which inexact estimates of the gradient and the Hessian information are used for various steps. Under certain conditions on the inexactness measures, we derive iteration complexity bounds for achieving |$\epsilon $|-approximate second-order optimality that match best-known lower bounds. Our inexactness condition on the gradient is adaptive, allowing for crude accuracy in regions with large gradients. We describe two variants of our approach, one in which the step size along the computed search direction is chosen adaptively, and another in which the step size is pre-defined. To obtain second-order optimality, our algorithms will make use of a negative curvature direction on some steps. These directions can be obtained, with high probability, using the randomized Lanczos algorithm. In this sense, all of our results hold with high probability over the run of the algorithm. We evaluate the performance of our proposed algorithms empirically on several machine learning models. Our approach is a first attempt to introduce inexact Hessian and/or gradient information into the Newton-CG algorithm of Royer & Wright (2018, Complexity analysis of second-order line-search algorithms for smooth nonconvex optimization. SIAM J. Optim., 28, 1448–1477).
- 22 August 2022
- Published by Oxford University Press (OUP) in IMA Journal of Numerical Analysis
- Vol. 43 (3) , 1855-1897
Inexact Newton-CG algorithms with complexity guarantees
We consider variants of a recently developed Newton-CG algorithm for nonconvex problems (Royer, C. W. & Wright, S. J. (2018) Complexity analysis of second-order line-search algorithms for smooth nonconvex optimization. SIAM J. Optim., 28, 1448–1477) in which inexact estimates of the gradient and the Hessian information are used for various steps. Under certain conditions on the inexactness measures, we derive iteration complexity bounds for achieving |$\epsilon $|-approximate second-order optimality that match best-known lower bounds. Our inexactness condition on the gradient is adaptive, allowing for crude accuracy in regions with large gradients. We describe two variants of our approach, one in which the step size along the computed search direction is chosen adaptively, and another in which the step size is pre-defined. To obtain second-order optimality, our algorithms will make use of a negative curvature direction on some steps. These directions can be obtained, with high probability, using the randomized Lanczos algorithm. In this sense, all of our results hold with high probability over the run of the algorithm. We evaluate the performance of our proposed algorithms empirically on several machine learning models. Our approach is a first attempt to introduce inexact Hessian and/or gradient information into the Newton-CG algorithm of Royer & Wright (2018, Complexity analysis of second-order line-search algorithms for smooth nonconvex optimization. SIAM J. Optim., 28, 1448–1477).
- Open Access
Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology
Trust and transparency are critical for deploying deep learning (DL) models into the clinic. DL application poses generalisation obstacles since training/development datasets often have different data distributions to clinical/production datasets that can lead to incorrect predictions with underestimated uncertainty. To investigate this pitfall, we benchmarked one pointwise and three approximate Bayesian DL models used to predict cancer of unknown primary with three independent RNA-seq datasets covering 10,968 samples across 57 primary cancer types. Our results highlight simple and scalable Bayesian DL significantly improves the generalisation of uncertainty estimation (e.g., p-value = 0.0013 for calibration). Moreover, we demonstrate Bayesian DL substantially improves accuracy under data distributional shifts when utilising ‘uncertainty thresholding’ by designing a prototypical metric that evaluates the expected (accuracy) loss when deploying models from development to production, which we call the Area between Development and Production curve (ADP). In summary, Bayesian DL is a hopeful avenue of research for generalising uncertainty, which improves performance, transparency, and therefore safety of DL models for deployment in real-world.
Open AccessGeneralising uncertainty improves accuracy and safety of deep learning analytics applied to oncology
Trust and transparency are critical for deploying deep learning (DL) models into the clinic. DL application poses generalisation obstacles since training/development datasets often have different data distributions to clinical/production datasets that can lead to incorrect predictions with underestimated uncertainty. To investigate this pitfall, we benchmarked one pointwise and three approximate Bayesian DL models used to predict cancer of unknown primary with three independent RNA-seq datasets covering 10,968 samples across 57 primary cancer types. Our results highlight simple and scalable Bayesian DL significantly improves the generalisation of uncertainty estimation (e.g., p-value = 0.0013 for calibration). Moreover, we demonstrate Bayesian DL substantially improves accuracy under data distributional shifts when utilising ‘uncertainty thresholding’ by designing a prototypical metric that evaluates the expected (accuracy) loss when deploying models from development to production, which we call the Area between Development and Production curve (ADP). In summary, Bayesian DL is a hopeful avenue of research for generalising uncertainty, which improves performance, transparency, and therefore safety of DL models for deployment in real-world.
- Open Access
- 8 July 2022
- Published by Elsevier in EURO Journal on Computational Optimization
- Vol. 10
Newton-MR: Inexact Newton Method with minimum residual sub-problem solver
- 8 July 2022
- Published by Elsevier in EURO Journal on Computational Optimization
- Vol. 10
Open AccessNewton-MR: Inexact Newton Method with minimum residual sub-problem solver