Binary Neural Networks (BNNs) are compact and efficient by using binary weights instead of real-valued weights. Current BNNs use latent real-valued weights during training, where several training hyper-parameters are inherited from real-valued networks. The interpretation of several of these hyperparameters is based on the magnitude of the real-valued weights. For BNNs, however, the magnitude of binary weights is not meaningful, and thus it is unclear what these hyperparameters actually do. One example is weight-decay, which aims to keep the magnitude of real-valued weights small. Other examples are latent weight initialization, the learning rate, and learning rate decay, which influence the magnitude of the real-valued weights. The magnitude is interpretable for real-valued weights, but loses its meaning for binary weights. In this paper we offer a new interpretation of these magnitude-based hyperparameters based on higher-order gradient filtering during network optimization. Our analysis makes it possible to understand how magnitude-based hyperparameters influence the training of binary networks which allows for new optimization filters specifically designed for binary neural networks that are independent of their real-valued interpretation. Moreover, our improved understanding reduces the number of hyperparameters, which in turn eases the hyperparameter tuning effort which may lead to better hyperparameter values for improved accuracy. Code is available at https://github.com/jorisquist/Understanding-WM-HP-in-BNNs
Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodology to improve the initialization. Instead of searching for better task-aware initialization, we focus on a complementary factor in MAML framework, inner-loop optimization (or fast adaptation). Consequently, we propose a new weight update rule that greatly enhances the fast adaptation process. Specifically, we introduce a small meta-network that can adaptively generate per-step hyperparameters: learning rate and weig…
We present a simple and powerful algorithm for parallel black box optimization called Successive Halving and Classification (SHAC). The algorithm operates in $K$ stages of parallel function evaluations and trains a cascade of binary classifiers to iteratively cull the undesirable regions of the search space. SHAC is easy to implement, requires no tuning of its own configuration parameters, is invariant to the scale of the objective function and can be built using any choice of binary classifier. We adopt tree-based classifiers within SHAC and achieve competitive performance against several str…
Google Research, Brain Team（谷歌研究院，大脑团队）；AAI, University of Technology Sydney（悉尼科技大学AAI）
Efficient hyperparameter or architecture search methods have shown remarkable results, but each of them is only applicable to searching for either hyperparameters (HPs) or architectures. In this work, we propose a unified pipeline, AutoHAS, to efficiently search for both architectures and hyperparameters. AutoHAS learns to alternately update the shared network weights and a reinforcement learning (RL) controller, which learns the probability distribution for the architecture candidates and HP candidates. A temporary weight is introduced to store the updated weight from the selected HPs (by the…
University of New South Wales（新南威尔士大学）；Australian National University（澳大利亚国立大学）
The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are …
Weight sharing promises to make neural architecture search (NAS) tractable even on commodity hardware. Existing methods in this space rely on a diverse set of heuristics to design and train the shared-weight backbone network, a.k.a. the super-net. Since heuristics and hyperparameters substantially vary across different methods, a fair comparison between them can only be achieved by systematically analyzing the influence of these factors. In this paper, we therefore provide a systematic evaluation of the heuristics and hyperparameters that are frequently employed by weight-sharing NAS algorithm…
Binary networks are extremely efficient as they use only two symbols to define the network: $\{+1,-1\}$. One can make the prior distribution of these symbols a design choice. The recent IR-Net of Qin et al. argues that imposing a Bernoulli distribution with equal priors (equal bit ratios) over the binary weights leads to maximum entropy and thus minimizes information loss. However, prior work cannot precisely control the binary weight distribution during training, and therefore cannot guarantee maximum entropy. Here, we show that quantizing using optimal transport can guarantee any bit ratio, …
Argonne National Laboratory（阿贡国家实验室）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）
The training of neural networks using different deep learning frameworks may lead to drastically differing accuracy levels despite the use of the same neural network architecture and identical training hyperparameters such as learning rate and choice of optimization algorithms. Currently, our ability to build standardized deep learning models is limited by the availability of a suite of neural network and corresponding training hyperparameter benchmarks that expose differences between existing deep learning frameworks. In this paper, we present a living dataset of models and hyperparameters, c…
University of Washington（华盛顿大学）；Columbia University（哥伦比亚大学）；Google Research（谷歌研究院）；Meta AI Research（Meta人工智能研究院）；Tel Aviv University（特拉维夫大学）
The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set, discarding the remainder. In this paper, we revisit the second step of this procedure in the context of fine-tuning large pre-trained models, where fine-tuned models often appear to lie in a single low error basin. We show that averaging the weights of multiple models fine-tuned with different hyperparameter configurations often improves accuracy and robustness. Unlike a conventional ensemble, we m…
Hasso Plattner Institute（哈索·普拉特纳研究所）；University of Potsdam（波茨坦大学）
Convolutional neural networks have achieved astonishing results in different application areas. Various methods which allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks seem to be a promising approach for these devices with low computational power. However, understanding binary neural networks and training accurate models for practical applications remains a challenge. In our work, we focus on increasing our understanding of the training process and making it accessible to everyone. We publish our code and models based on BMXNet fo…
École Polytechnique de Montréal（蒙特利尔综合理工学院）；Université de Montréal（蒙特利尔大学）
Deep Neural Networks (DNN) have achieved state-of-the-art results in a wide range of tasks, with the best results obtained with large training sets and large models. In the past, GPUs enabled these breakthroughs because of their greater computational speed. In the future, faster computation at both training and test time is likely to be crucial for further progress and for consumer applications on low-power devices. As a result, there is much interest in research and development of dedicated hardware for Deep Learning (DL). Binary weights, i.e., weights which are constrained to only two possib…
Loss functions drive the optimization of machine learning algorithms. The choice of a loss function can have a significant impact on the training of a model, and how the model learns the data. Binary classification is one of the major pillars of machine learning problems, used in medical imaging to failure detection applications. The most commonly used surrogate loss functions for binary classification include the binary cross-entropy and the hinge loss functions, which form the focus of our study. In this paper, we provide an overview of a novel loss function, the Xtreme Margin loss function.…
ETH Zürich（苏黎世联邦理工学院）；Università di Bologna（博洛尼亚大学）
We present Random Partition Relaxation (RPR), a method for strong quantization of neural networks weight to binary (+1/-1) and ternary (+1/0/-1) values. Starting from a pre-trained model, we quantize the weights and then relax random partitions of them to their continuous values for retraining before re-quantizing them and switching to another weight partition for further adaptation. We demonstrate binary and ternary-weight networks with accuracies beyond the state-of-the-art for GoogLeNet and competitive performance for ResNet-18 and ResNet-50 using an SGD-based training method that can easil…
Prompt-to-Prompt: Text-Based Image Editing Via Cross-Attention Mechanisms -- The Research of Hyperparameters and Novel Mechanisms to Enhance Existing Frameworks
University of California at Los Angeles（加州大学洛杉矶分校）；University of California at Irvine（加州大学欧文分校）
We propose BinaryRelax, a simple two-phase algorithm, for training deep neural networks with quantized weights. The set constraint that characterizes the quantization of weights is not imposed until the late stage of training, and a sequence of \emph{pseudo} quantized weights is maintained. Specifically, we relax the hard constraint into a continuous regularizer via Moreau envelope, which turns out to be the squared Euclidean distance to the set of quantized weights. The pseudo quantized weights are obtained by linearly interpolating between the float weights and their quantizations. A continu…
