Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInterpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks
110
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
In this paper we explore acceleration techniques for large scale nonconvex optimization problems with special focuses on deep neural networks. The extrapolation scheme is a classical approach for accelerating stochastic gradient descent for convex optimization, but it does not work well for nonconvex optimization typically. Alternatively, we propose an interpolation scheme to accelerate nonconvex optimization and call the method Interpolatron. We explain motivation behind Interpolatron and conduct a thorough empirical analysis. Empirical results on DNNs of great depths (e.g., 98-layer ResNet and 200-layer ResNet) on CIFAR-10 and ImageNet show that Interpolatron can converge much faster than the state-of-the-art methods such as the SGD with momentum and Adam. Furthermore, Andersons acceleration, in which mixing coefficients are computed by least-squares estimation, can also be used to improve the performance. Both Interpolatron and Andersons acceleration are easy to implement and tune. We also show that Interpolatron has linear convergence rate under certain regularity assumptions.
rate research
Read More
Deep neural networks have yielded superior performance in many applications; however, the gradient computation in a deep model with millions of instances lead to a lengthy training process even with modern GPU/TPU hardware acceleration. In this paper, we propose AutoAssist, a simple framework to accelerate training of a deep neural network. Typically, as the training procedure evolves, the amount of improvement in the current model by a stochastic gradient update on each instance varies dynamically. In AutoAssist, we utilize this fact and design a simple instance shrinking operation, which is used to filter out instances with relatively low marginal improvement to the current model; thus the computationally intensive gradient computations are performed on informative instances as much as possible. We prove that the proposed technique outperforms vanilla SGD with existing importance sampling approaches for linear SVM problems, and establish an O(1/k) convergence for strongly convex problems. In order to apply the proposed techniques to accelerate training of deep models, we propose to jointly train a very lightweight Assistant network in addition to the original deep network referred to as Boss. The Assistant network is designed to gauge the importance of a given instance with respect to the current Boss such that a shrinking operation can be applied in the batch generator. With careful design, we train the Boss and Assistant in a nonblocking and asynchronous fashion such that overhead is minimal. We demonstrate that AutoAssist reduces the number of epochs by 40% for training a ResNet to reach the same test accuracy on an image classification data set and saves 30% training time needed for a transformer model to yield the same BLEU scores on a translation dataset.
Recent advances in deep learning have made the use of large, deep neural networks with tens of millions of parameters. The sheer size of these networks imposes a challenging computational burden during inference. Existing work focuses primarily on accelerating each forward pass of a neural network. Inspired by the group testing strategy for efficient disease testing, we propose neural group testing, which accelerates by testing a group of samples in one forward pass. Groups of samples that test negative are ruled out. If a group tests positive, samples in that group are then retested adaptively. A key challenge of neural group testing is to modify a deep neural network so that it could test multiple samples in one forward pass. We propose three designs to achieve this without introducing any new parameters and evaluate their performances. We applied neural group testing in an image moderation task to detect rare but inappropriate images. We found that neural group testing can group up to 16 images in one forward pass and reduce the overall computation cost by over 73% while improving detection performance.
Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations. It relies on querying a distribution over functions defined by a relatively cheap surrogate model. An accurate model for this distribution over functions is critical to the effectiveness of the approach, and is typically fit using Gaussian processes (GPs). However, since GPs scale cubically with the number of observations, it has been challenging to handle objectives whose optimization requires many evaluations, and as such, massively parallelizing the optimization. In this work, we explore the use of neural networks as an alternative to GPs to model distributions over functions. We show that performing adaptive basis function regression with a neural network as the parametric form performs competitively with state-of-the-art GP-based approaches, but scales linearly with the number of data rather than cubically. This allows us to achieve a previously intractable degree of parallelism, which we apply to large scale hyperparameter optimization, rapidly finding competitive models on benchmark object recognition tasks using convolutional networks, and image caption generation using neural language models.
We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical evidence indicating that networks corresponding to lower-lying minima in the optimization landscape of the learning objective tend to be more robust. The robustness estimate used is the inverse of a proposed sensitivity measure, which we define as the volume of an over-approximation of the reachable set of network outputs under all additive $l_{infty}$-bounded perturbations on the input data. We present a novel loss function which includes a sensitivity term in addition to the traditional task-oriented and regularization terms. In our experiments on standard machine learning and computer vision datasets, we show that the proposed loss function leads to networks which reliably optimize the robustness measure as well as other related metrics of adversarial robustness without significant degradation in the classification error. Experimental results indicate that the proposed method outperforms state-of-the-art sensitivity-based learning approaches with regards to robustness to adversarial attacks. We also show that although the introduced framework does not explicitly enforce an adversarial loss, it achieves competitive overall performance relative to methods that do.
Training quantum neural networks (QNNs) using gradient-based or gradient-free classical optimisation approaches is severely impacted by the presence of barren plateaus in the cost landscapes. In this paper, we devise a framework for leveraging quantum optimisation algorithms to find optimal parameters of QNNs for certain tasks. To achieve this, we coherently encode the cost function of QNNs onto relative phases of a superposition state in the Hilbert space of the network parameters. The parameters are tuned with an iterative quantum optimisation structure using adaptively selected Hamiltonians. The quantum mechanism of this framework exploits hidden structure in the QNN optimisation problem and hence is expected to provide beyond-Grover speed up, mitigating the barren plateau issue.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
