Modular Duality in Deep Learning

• URL: http://arxiv.org/abs/2410.21265v1
• Date: Mon, 28 Oct 2024 17:57:31 GMT
• Title: Modular Duality in Deep Learning
• Authors: Jeremy Bernstein, Laker Newhouse,
• Abstract summary: We construct a duality map for general neural networks. Our map forms a unifying theoretical basis for training algorithms that are a) fast and b) scalable. Our iteration was recently used to set new speed records for training NanoGPT.
• Score: 3.471637998699967
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An old idea in optimization theory says that since the gradient is a dual vector it may not be subtracted from the weights without first being mapped to the primal space where the weights reside. We take this idea seriously in this paper and construct such a duality map for general neural networks. Our map, which we call modular dualization, forms a unifying theoretical basis for training algorithms that are a) fast and b) scalable. Modular dualization involves first assigning operator norms to layers based on the semantics of each layer, and then using these layerwise norms to recursively induce a duality map on the weight space of the full neural architecture. We conclude by deriving GPU-friendly algorithms for dualizing Embed, Linear and Conv2D layers -- the latter two methods are based on a new rectangular Newton-Schulz iteration that we propose. Our iteration was recently used to set new speed records for training NanoGPT. Overall, we hope that our theory of modular duality will yield a next generation of fast and scalable optimizers for general neural architectures.

Related papers

• Riemannian Optimization in Modular Systems [0.006486143522483092]
  The backpropagation algorithm is instrumental in the success of neural networks.<n>Despite its empirical success, a strong theoretical understanding of it is lacking.<n>We develop a framework of composable Riemannian modules'' whose convergence properties can be quantified.
  arXiv  Detail & Related papers  (2026-03-04T00:47:29Z)
• Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods [50.070182958880146]
  We propose a unified framework generalizing descent, quasi-Newton methods, and adaptive methods through the novel notion of preconditioned matrix norms.<n>Within this framework, we provide the first systematic treatment of affine and scale invariance in the matrix- parameterized setting.<n>We introduce two new methods, $ttMuAdam$ and $texttMuAdam-SANIA$, which combine the spectral geometry of Muon with Adam-style preconditioning.
  arXiv  Detail & Related papers  (2025-10-12T19:39:41Z)
• Sequential-Parallel Duality in Prefix Scannable Models [68.39855814099997]
  Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba.<n>This raises a natural question: can we characterize the full class of neural sequence models that support near-constant-time parallel evaluation and linear-time, constant-space sequential inference?
  arXiv  Detail & Related papers  (2025-06-12T17:32:02Z)
• Old Optimizer, New Norm: An Anthology [3.471637998699967]
  We argue that each method can instead be understood as a squarely first-order method without convexity assumptions. By generalizing this observation, we chart a new design space for training algorithms. We hope that this idea of carefully metrizing the neural architecture might lead to more stable, scalable and indeed faster training.
  arXiv  Detail & Related papers  (2024-09-30T14:26:12Z)
• A foundation for exact binarized morphological neural networks [2.8925699537310137]
  Training and running deep neural networks (NNs) often demands a lot of computation and energy-intensive specialized hardware. One way to reduce the computation and power cost is to use binary weight NNs, but these are hard to train because the sign function has a non-smooth gradient. We present a model based on Mathematical Morphology (MM), which can binarize ConvNets without losing performance under certain conditions.
  arXiv  Detail & Related papers  (2024-01-08T11:37:44Z)
• Automatic Optimisation of Normalised Neural Networks [1.0334138809056097]
  We propose automatic optimisation methods considering the geometry of matrix manifold for the normalised parameters of neural networks. Our approach first initialises the network and normalises the data with respect to the $ell2$-$ell2$ gain of the initialised network.
  arXiv  Detail & Related papers  (2023-12-17T10:13:42Z)
• Automatic Gradient Descent: Deep Learning without Hyperparameters [35.350274248478804]
  The architecture of a deep neural network is defined explicitly in terms of the number of layers, the width of each layer and the general network topology. Paper builds a new framework for deriving objective functions: gradient idea is to transform a Bregman divergence to account for the non gradient structure of neural architecture.
  arXiv  Detail & Related papers  (2023-04-11T12:45:52Z)
• Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining [61.09807522366773]
  We introduce an algorithm that approximates the softmax with provable bounds and that dynamically maintains the tree. In our study on datasets with over twenty million targets, our approach cuts error by half in relation to oracle brute-force negative mining.
  arXiv  Detail & Related papers  (2023-03-27T15:18:32Z)
• A Unified Algebraic Perspective on Lipschitz Neural Networks [88.14073994459586]
  This paper introduces a novel perspective unifying various types of 1-Lipschitz neural networks. We show that many existing techniques can be derived and generalized via finding analytical solutions of a common semidefinite programming (SDP) condition. Our approach, called SDP-based Lipschitz Layers (SLL), allows us to design non-trivial yet efficient generalization of convex potential layers.
  arXiv  Detail & Related papers  (2023-03-06T14:31:09Z)
• Improved Convergence Guarantees for Shallow Neural Networks [91.3755431537592]
  We prove convergence of depth 2 neural networks, trained via gradient descent, to a global minimum. Our model has the following features: regression with quadratic loss function, fully connected feedforward architecture, RelU activations, Gaussian data instances, adversarial labels. They strongly suggest that, at least in our model, the convergence phenomenon extends well beyond the NTK regime''
  arXiv  Detail & Related papers  (2022-12-05T14:47:52Z)
• Unified Field Theory for Deep and Recurrent Neural Networks [56.735884560668985]
  We present a unified and systematic derivation of the mean-field theory for both recurrent and deep networks. We find that convergence towards the mean-field theory is typically slower for recurrent networks than for deep networks. Our method exposes that Gaussian processes are but the lowest order of a systematic expansion in $1/n$.
  arXiv  Detail & Related papers  (2021-12-10T15:06:11Z)
• SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models [15.541264326378366]
  In recent years, implicit deep learning has emerged as a method to increase the depth of deep neural networks. The training is performed as a bi-level problem, and its computational complexity is partially driven by the iterative inversion of a huge Jacobian matrix. We propose a novel strategy to tackle this computational bottleneck from which many bi-level problems suffer.
  arXiv  Detail & Related papers  (2021-06-01T15:07:34Z)
• Leveraging Non-uniformity in First-order Non-convex Optimization [93.6817946818977]
  Non-uniform refinement of objective functions leads to emphNon-uniform Smoothness (NS) and emphNon-uniform Lojasiewicz inequality (NL) New definitions inspire new geometry-aware first-order methods that converge to global optimality faster than the classical $Omega (1/t2)$ lower bounds.
  arXiv  Detail & Related papers  (2021-05-13T04:23:07Z)
• Dual-constrained Deep Semi-Supervised Coupled Factorization Network with Enriched Prior [80.5637175255349]
  We propose a new enriched prior based Dual-constrained Deep Semi-Supervised Coupled Factorization Network, called DS2CF-Net. To ex-tract hidden deep features, DS2CF-Net is modeled as a deep-structure and geometrical structure-constrained neural network. Our network can obtain state-of-the-art performance for representation learning and clustering.
  arXiv  Detail & Related papers  (2020-09-08T13:10:21Z)
• On Second Order Behaviour in Augmented Neural ODEs [69.8070643951126]
  We consider Second Order Neural ODEs (SONODEs) We show how the adjoint sensitivity method can be extended to SONODEs. We extend the theoretical understanding of the broader class of Augmented NODEs (ANODEs)
  arXiv  Detail & Related papers  (2020-06-12T14:25:31Z)
• Scalable Second Order Optimization for Deep Learning [34.12384996822749]
  We present a scalable implementation of a second-order preconditioned method (concretely, a variant of full-matrix Adagrad) Our novel design effectively utilizes the prevalent heterogeneous hardware architecture for training deep models, consisting of a multicore CPU coupled with multiple accelerator units. We demonstrate superior performance compared to state-of-the-art on very large learning tasks such as machine translation with Transformers, language modeling with BERT, click-through rate prediction on Criteo, and image classification on ImageNet with ResNet-50.
  arXiv  Detail & Related papers  (2020-02-20T20:51:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.