ترغب بنشر مسار تعليمي؟ اضغط هنا

Sparse Flows: Pruning Continuous-depth Models

128   0   0.0 ( 0 )
 نشر من قبل Lucas Liebenwein
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Continuous deep learning architectures enable learning of flexible probabilistic models for predictive modeling as neural ordinary differential equations (ODEs), and for generative modeling as continuous normalizing flows. In this work, we design a framework to decipher the internal dynamics of these continuous depth models by pruning their network architectures. Our empirical results suggest that pruning improves generalization for neural ODEs in generative modeling. Moreover, pruning finds minimal and efficient neural ODE representations with up to 98% less parameters compared to the original network, without loss of accuracy. Finally, we show that by applying pruning we can obtain insightful information about the design of better neural ODEs.We hope our results will invigorate further research into the performance-size trade-offs of modern continuous-depth models.



قيم البحث

اقرأ أيضاً

Continuous-depth neural models, where the derivative of the models hidden state is defined by a neural network, have enabled strong sequential data processing capabilities. However, these models rely on advanced numerical differential equation (DE) s olvers resulting in a significant overhead both in terms of computational cost and model complexity. In this paper, we present a new family of models, termed Closed-form Continuous-depth (CfC) networks, that are simple to describe and at least one order of magnitude faster while exhibiting equally strong modeling abilities compared to their ODE-based counterparts. The models are hereby derived from the analytical closed-form solution of an expressive subset of time-continuous models, thus alleviating the need for complex DE solvers all together. In our experimental evaluations, we demonstrate that CfC networks outperform advanced, recurrent models over a diverse set of time-series prediction tasks, including those with long-term dependencies and irregularly sampled data. We believe our findings open new opportunities to train and deploy rich, continuous neural models in resource-constrained settings, which demand both performance and efficiency.
We introduce a new stochastic verification algorithm that formally quantifies the behavioral robustness of any time-continuous process formulated as a continuous-depth model. The algorithm solves a set of global optimization (Go) problems over a give n time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states. We call our algorithm GoTube. Through its construction, GoTube ensures that the bounding tube is conservative up to a desired probability. GoTube is implemented in JAX and optimized to scale to complex continuous-depth models. Compared to advanced reachability analysis tools for time-continuous neural networks, GoTube provably does not accumulate over-approximation errors between time steps and avoids the infamous wrapping effect inherent in symbolic techniques. We show that GoTube substantially outperforms state-of-the-art verification tools in terms of the size of the initial ball, speed, time-horizon, task completion, and scalability, on a large set of experiments. GoTube is stable and sets the state-of-the-art for its ability to scale up to time horizons well beyond what has been possible before.
We introduce the framework of continuous-depth graph neural networks (GNNs). Neural graph differential equations (Neural GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determined by a continuum of GNN layers, b lending discrete topological structures and differential equations. The proposed framework is shown to be compatible with static GNN models and is extended to dynamic and stochastic settings through hybrid dynamical system theory. Here, Neural GDEs improve performance by exploiting the underlying dynamics geometry, further introducing the ability to accommodate irregularly sampled data. Results prove the effectiveness of the proposed models across applications, such as traffic forecasting or prediction in genetic regulatory networks.
The infinite-depth paradigm pioneered by Neural ODEs has launched a renaissance in the search for novel dynamical system-inspired deep learning primitives; however, their utilization in problems of non-trivial size has often proved impossible due to poor computational scalability. This work paves the way for scalable Neural ODEs with time-to-prediction comparable to traditional discrete networks. We introduce hypersolvers, neural networks designed to solve ODEs with low overhead and theoretical guarantees on accuracy. The synergistic combination of hypersolvers and Neural ODEs allows for cheap inference and unlocks a new frontier for practical application of continuous-depth models. Experimental evaluations on standard benchmarks, such as sampling for continuous normalizing flows, reveal consistent pareto efficiency over classical numerical methods.
Exponential families are widely used in machine learning; they include many distributions in continuous and discrete domains (e.g., Gaussian, Dirichlet, Poisson, and categorical distributions via the softmax transformation). Distributions in each of these families have fixed support. In contrast, for finite domains, there has been recent works on sparse alternatives to softmax (e.g. sparsemax, $alpha$-entmax, and fusedmax) and corresponding losses, which have varying support. This paper expands that line of work in several directions: first, it extends $Omega$-regularized prediction maps and Fenchel-Young losses to arbitrary domains (possibly countably infinite or continuous). For linearly parametrized families, we show that minimization of Fenchel-Young losses is equivalent to moment matching of the statistics, generalizing a fundamental property of exponential families. When $Omega$ is a Tsallis negentropy with parameter $alpha$, we obtain deformed exponential families, which include $alpha$-entmax and sparsemax ($alpha$ = 2) as particular cases. For quadratic energy functions in continuous domains, the resulting densities are $beta$-Gaussians, an instance of elliptical distributions that contain as particular cases the Gaussian, biweight, triweight and Epanechnikov densities, and for which we derive closed-form expressions for the variance, Tsallis entropy, and Fenchel-Young loss. When $Omega$ is a total variation or Sobolev regularizer, we obtain a continuous version of the fusedmax. Finally, we introduce continuous-domain attention mechanisms, deriving efficient gradient backpropagation algorithms for $alpha in {1, 4/3, 3/2, 2}$. Using them, we demonstrate our sparse continuous distributions for attention-based audio classification and visual question answering, showing that they allow attending to time intervals and compact regions.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا