Search Results for author:
Found 9 papers, 0 papers with code
Upper and lower bounds for the Lipschitz constant of random neural networks
Empirical studies have widely demonstrated that neural networks are highly sensitive to small, adversarial perturbations of the input.
Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing
We show that in this setting, factorized gradient descent enjoys two implicit properties: (1) coupling of the trajectory of gradient descent where the factors are coupled in various ways throughout the gradient update trajectory and (2) an algorithmic regularization property where the iterates show a propensity towards low-rank models despite the overparameterized nature of the factorized model.
How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?
Reformulation of blind deconvolution as a low-rank recovery problem has led to multiple theoretical recovery guarantees in the past decade due to the success of the nuclear norm minimization heuristic.
Randomly Initialized Alternating Least Squares: Fast Convergence for Matrix Sensing
In this paper, we show that ALS with random initialization converges to the true solution with $\varepsilon$-accuracy in $O(\log n + \log (1/\varepsilon)) $ iterations using only a near-optimal amount of samples, where we assume the measurement matrices to be i. i. d.
Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction
Recently there has been significant theoretical progress on understanding the convergence and generalization of gradient-based methods on nonconvex losses with overparameterized models.
Understanding Overparameterization in Generative Adversarial Networks
We also empirically study the role of model overparameterization in GANs using several large-scale experiments on CIFAR-10 and Celeb-A datasets.
Understanding Over-parameterization in Generative Adversarial Networks
In this work, we present a comprehensive analysis of the importance of model over-parameterization in GANs both theoretically and empirically.
Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate
The recovery of sparse data is at the core of many applications in machine learning and signal processing.
On the convex geometry of blind deconvolution and matrix completion
We find that for both these applications the dimension factors in the noise bounds are not an artifact of the proof, but the problems are intrinsically badly conditioned.
