skip to main content

Explore Research Products in the NSF-PAR

Title: HyLo: a hybrid low-rank natural gradient descent method
This work presents a Hybrid Low-Rank Natural Gradient Descent method, called HyLo, that accelerates the training time of deep neural networks. Natural gradient descent (NGD) requires computing the inverse of the Fisher information matrix (FIM), which is typically expensive at large-scale. Kronecker factorization methods such as KFAC attempt to improve NGD's running time by approximating the FIM with Kronecker factors. However, the size of Kronecker factors increases quadratically as the model size grows. Instead, in HyLo, we use the Sherman-Morrison-Woodbury variant of NGD (SNGD) and propose a reformulation of SNGD to resolve its scalability issues. HyLo uses a computationally-efficient low-rank factorization to achieve superior timing for Fisher inverses. We evaluate HyLo on large models including ResNet-50, U-Net, and ResNet-32 on up to 64 GPUs. HyLo converges 1.4×-2.1× faster than the state-of-the-art distributed implementation of KFAC and reduces the computation and communication time up to 350× and 10.7× on ResNet-50.  more » « less
Award ID(s):
1814888 2053485
NSF-PAR ID:
10399586
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis
Volume:
47
Page Range / eLocation ID:
1-16
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ( , IEEE Conference on Computer Vision and Pattern Recognition)
    We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank factorization of the features that requires more memory, or select only a subset of features by pruning entire filter channels. We propose the Cascaded Projection (CaP) compression method that projects the output and input filter channels of successive layers to a unified low dimensional space based on a low-rank projection. We optimize the projection to minimize classification loss and the difference between the next layer’s features in the compressed and uncompressed networks. To solve this non-convex optimization problem we propose a new optimization method of a proxy matrix using back propagation and Stochastic Gradient Descent (SGD) with geometric constraints. Our cascaded projection approach leads to improvements in all critical areas of network compression: high accuracy, low memory consumption, low parameter count and high processing speed. The proposed CaP method demonstrates state-of-the-art results compressing VGG16 and ResNet networks with over 4× reduction in the number of computations and excellent performance in top-5 accuracy on the ImageNet dataset before and after fine-tuning. 
    more » « less
  2. ; ; ; ( , Proceedings of the 40th International Conference on Machine Learning)
    Krause, Andreas ; Brunskill, Emma ; Cho, Kyunghyun ; Engelhardt, Barbara ; Sabato, Sivan ; Scarlett, Jonathan (Ed.)
    We consider a deep matrix factorization model of covariance matrices trained with the Bures-Wasserstein distance. While recent works have made advances in the study of the optimization problem for overparametrized low-rank matrix approximation, much emphasis has been placed on discriminative settings and the square loss. In contrast, our model considers another type of loss and connects with the generative setting. We characterize the critical points and minimizers of the Bures-Wasserstein distance over the space of rank-bounded matrices. The Hessian of this loss at low-rank matrices can theoretically blow up, which creates challenges to analyze convergence of gradient optimization methods. We establish convergence results for gradient flow using a smooth perturbative version of the loss as well as convergence results for finite step size gradient descent under certain assumptions on the initial weights. 
    more » « less
  3. ( , International conference on learning representations (ICLR))
    null (Ed.)
    Recently mean field theory has been successfully used to analyze properties of wide, random neural networks. It gave rise to a prescriptive theory for initializing feed-forward neural networks with orthogonal weights, which ensures that both the forward propagated activations and the backpropagated gradients are near isometries and as a consequence training is orders of magnitude faster. Despite strong empirical performance, the mechanisms by which critical initializations confer an advantage in the optimization of deep neural networks are poorly understood. Here we show a novel connection between the maximum curvature of the optimization landscape (gradient smoothness) as measured by the Fisher information matrix (FIM) and the spectral radius of the input-output Jacobian, which partially explains why more isometric networks can train much faster. Furthermore, given that orthogonal weights are necessary to ensure that gradient norms are approximately preserved at initialization, we experimentally investigate the benefits of maintaining orthogonality throughout training, and we conclude that manifold optimization of weights performs well regardless of the smoothness of the gradients. Moreover, we observe a surprising yet robust behavior of highly isometric initializations --- even though such networks have a lower FIM condition number \emph{at initialization}, and therefore by analogy to convex functions should be easier to optimize, experimentally they prove to be much harder to train with stochastic gradient descent. We conjecture the FIM condition number plays a non-trivial role in the optimization. 
    more » « less
  4. ( , AISTATS)
    The success of gradient descent in ML and especially for learning neural networks is remarkable and robust. In the context of how the brain learns, one aspect of gradient descent that appears biologically difficult to realize (if not implausible) is that its updates rely on feedback from later layers to earlier layers through the same connections. Such bidirected links are relatively few in brain networks, and even when reciprocal connections exist, they may not be equi-weighted. Random Feedback Alignment (Lillicrap et al., 2016), where the backward weights are random and fixed, has been proposed as a bio-plausible alternative and found to be effective empirically. We investigate how and when feedback alignment (FA) works, focusing on one of the most basic problems with layered structure n×m, the goal is to find a low rank factorization Zn×rWr×m that minimizes the error ∥ZW−Y∥F. Gradient descent solves this problem optimally. We show that FA finds the optimal solution when r≥rank(Y). We also shed light on how FA works. It is observed empirically that the forward weight matrices and (random) feedback matrices come closer during FA updates. Our analysis rigorously derives this phenomenon and shows how it facilitates convergence of FA*, a closely related variant of FA. We also show that FA can be far from optimal when r more » « less
  5. ; ( , AISTATS)
    The success of gradient descent in ML and especially for learning neural networks is remarkable and robust. In the context of how the brain learns, one aspect of gradient descent that appears biologically difficult to realize (if not implausible) is that its updates rely on feedback from later layers to earlier layers through the same connections. Such bidirected links are relatively few in brain networks, and even when reciprocal connections exist, they may not be equi-weighted. Random Feedback Alignment (Lillicrap et al., 2016), where the backward weights are random and fixed, has been proposed as a bio-plausible alternative and found to be effective empirically. We investigate how and when feedback alignment (FA) works, focusing on one of the most basic problems with layered structure n×m, the goal is to find a low rank factorization Zn×rWr×m that minimizes the error ∥ZW−Y∥F. Gradient descent solves this problem optimally. We show that FA finds the optimal solution when r≥rank(Y). We also shed light on how FA works. It is observed empirically that the forward weight matrices and (random) feedback matrices come closer during FA updates. Our analysis rigorously derives this phenomenon and shows how it facilitates convergence of FA*, a closely related variant of FA. We also show that FA can be far from optimal when r more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email