Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGuideBP: Guiding Backpropagation Through Weaker Pathways of Parallel Logits
113
0
0.0
(
0
)
Added by
Nibaran Das
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Convolutional neural networks often generate multiple logits and use simple techniques like addition or averaging for loss computation. But this allows gradients to be distributed equally among all paths. The proposed approach guides the gradients of backpropagation along weakest concept representations. A weakness scores defines the class specific performance of individual pathways which is then used to create a logit that would guide gradients along the weakest pathways. The proposed approach has been shown to perform better than traditional column merging techniques and can be used in several application scenarios. Not only can the proposed model be used as an efficient technique for training multiple instances of a model parallely, but also CNNs with multiple output branches have been shown to perform better with the proposed upgrade. Various experiments establish the flexibility of the learning technique which is simple yet effective in various multi-objective scenarios both empirically and statistically.
rate research
Read More
Neural Architecture Search (NAS) often trains and evaluates a large number of architectures. Recent predictor-based NAS approaches attempt to address such heavy computation costs with two key steps: sampling some architecture-performance pairs and fitting a proxy accuracy predictor. Given limited samples, these predictors, however, are far from accurate to locate top architectures due to the difficulty of fitting the huge search space. This paper reflects on a simple yet crucial question: if our final goal is to find the best architecture, do we really need to model the whole space well?. We propose a paradigm shift from fitting the whole architecture space using one strong predictor, to progressively fitting a search path towards the high-performance sub-space through a set of weaker predictors. As a key property of the proposed weak predictors, their probabilities of sampling better architectures keep increasing. Hence we only sample a few well-performed architectures guided by the previously learned predictor and estimate a new better weak predictor. This embarrassingly easy framework produces coarse-to-fine iteration to refine the ranking of sampling space gradually. Extensive experiments demonstrate that our method costs fewer samples to find top-performance architectures on NAS-Bench-101 and NAS-Bench-201, as well as achieves the state-of-the-art ImageNet performance on the NASNet search space. In particular, compared to state-of-the-art (SOTA) predictor-based NAS methods, WeakNAS outperforms all of them with notable margins, e.g., requiring at least 7.5x less samples to find global optimal on NAS-Bench-101; and WeakNAS can also absorb them for further performance boost. We further strike the new SOTA result of 81.3% in the ImageNet MobileNet Search Space. The code is available at https://github.com/VITA-Group/WeakNAS.
Machine/deep-learning (ML/DL) based techniques are emerging as a driving force behind many cutting-edge technologies, achieving high accuracy on computer vision workloads such as image classification and object detection. However, training these models involving large parameters is both time-consuming and energy-hogging. In this regard, several prior works have advocated for sparsity to speed up the of DL training and more so, the inference phase. This work begins with the observation that during training, sparsity in the forward and backward passes are correlated. In that context, we investigate two types of sparsity (input and output type) inherent in gradient descent-based optimization algorithms and propose a hardware micro-architecture to leverage the same. Our experimental results use five state-of-the-art CNN models on the Imagenet dataset, and show back propagation speedups in the range of 1.69$times$ to 5.43$times$, compared to the dense baseline execution. By exploiting sparsity in both the forward and backward passes, speedup improvements range from 1.68$times$ to 3.30$times$ over the sparsity-agnostic baseline execution. Our work also achieves significant reduction in training iteration time over several previously proposed dense as well as sparse accelerator based platforms, in addition to achieving order of magnitude energy efficiency improvements over GPU based execution.
We propose proximal backpropagation (ProxProp) as a novel algorithm that takes implicit instead of explicit gradient steps to update the network parameters during neural network training. Our algorithm is motivated by the step size limitation of explicit gradient descent, which poses an impediment for optimization. ProxProp is developed from a general point of view on the backpropagation algorithm, currently the most common technique to train neural networks via stochastic gradient descent and variants thereof. Specifically, we show that backpropagation of a prediction error is equivalent to sequential gradient descent steps on a quadratic penalty energy, which comprises the network activations as variables of the optimization. We further analyze theoretical properties of ProxProp and in particular prove that the algorithm yields a descent direction in parameter space and can therefore be combined with a wide variety of convergent algorithms. Finally, we devise an efficient numerical implementation that integrates well with popular deep learning frameworks. We conclude by demonstrating promising numerical results and show that ProxProp can be effectively combined with common first order optimizers such as Adam.
Poisoning attacks have emerged as a significant security threat to machine learning (ML) algorithms. It has been demonstrated that adversaries who make small changes to the training set, such as adding specially crafted data points, can hurt the performance of the output model. Most of these attacks require the full knowledge of training data or the underlying data distribution. In this paper we study the power of oblivious adversaries who do not have any information about the training set. We show a separation between oblivious and full-information poisoning adversaries. Specifically, we construct a sparse linear regression problem for which LASSO estimator is robust against oblivious adversaries whose goal is to add a non-relevant features to the model with certain poisoning budget. On the other hand, non-oblivious adversaries, with the same budget, can craft poisoning examples based on the rest of the training data and successfully add non-relevant features to the model.
Gradient-based optimization is the foundation of deep learning and reinforcement learning. Even when the mechanism being optimized is unknown or not differentiable, optimization using high-variance or biased gradient estimates is still often the best strategy. We introduce a general framework for learning low-variance, unbiased gradient estimators for black-box functions of random variables. Our method uses gradients of a neural network trained jointly with model parameters or policies, and is applicable in both discrete and continuous settings. We demonstrate this framework for training discrete latent-variable models. We also give an unbiased, action-conditional extension of the advantage actor-critic reinforcement learning algorithm.
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
