Diverse Imagenet Models Transfer Better

A commonly accepted hypothesis is that models with higher accuracy on Imagenet perform better on other downstream tasks, leading to much research dedicated to optimizing Imagenet accuracy. Recently this hypothesis has been challenged by evidence showing that self-supervised models transfer better than their supervised counterparts, despite their inferior Imagenet accuracy. This calls for identifying the additional factors, on top of Imagenet accuracy, that make models transferable. In this work we show that high diversity of the features learnt by the model promotes transferability jointly with Imagenet accuracy. Encouraged by the recent transferability results of self-supervised models, we propose a method that combines self-supervised and supervised pretraining to generate models with both high diversity and high accuracy, and as a result high transferability. We demonstrate our results on several architectures and multiple downstream tasks, including both single-label and multi-label classification.

IQNAS: Interpretable Integer Quadratic Programming Neural Architecture Search

Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS). However, previous methods use complicated predictors for the accuracy of the network. Those predictors are hard to interpret and sensitive to many hyperparameters to be tuned, hence, the resulting accuracy of the generated models is often harmed. In this work we resolve this by introducing Interpretable Integer Quadratic programming Neural Architecture Search (IQNAS), that is based on an accurate and simple quadratic formulation of both the accuracy predictor and the expected resource requirement, together with a scalable search method with theoretical guarantees. The simplicity of our proposed predictor together with the intuitive way it is constructed bring interpretability through many insights about the contribution of different design choices. For example, we find that in the examined search space, adding depth and width is more effective at deeper stages of the network and at the beginning of each resolution stage. Our experiments show that IQNAS generates comparable to or better architectures than other state-of-the-art NAS methods within a reduced search cost for each additional generated network, while strictly satisfying the resource constraints.

HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS), however, previous methods enforce the constraint only softly. Therefore, the resulting networks do not exactly adhere to the resource constraint and their accuracy is harmed. In this work we resolve this by introducing Hard Constrained diffeRentiable NAS (HardCoRe-NAS), that is based on an accurate formulation of the expected resource requirement and a scalable search method that satisfies the hard constraint throughout the search. Our experiments show that HardCoRe-NAS generates state-of-the-art architectures, surpassing other NAS methods, while strictly satisfying the hard resource constraints without any tuning required.

CobBO: Coordinate Backoff Bayesian Optimization

Bayesian optimization is a popular method for optimizing expensive black-box functions. The objective functions of hard real world problems are oftentimes characterized by a fluctuated landscape of many local optima. Bayesian optimization risks in over-exploiting such traps, remaining with insufficient query budget for exploring the global landscape. We introduce Coordinate Backoff Bayesian Optimization (CobBO) to alleviate those challenges. CobBO captures a smooth approximation of the global landscape by interpolating the values of queried points projected to randomly selected promising subspaces. Thus also a smaller query budget is required for the Gaussian process regressions applied over the lower dimensional subspaces. This approach can be viewed as a variant of coordinate ascent, tailored for Bayesian optimization, using a stopping rule for backing off from a certain subspace and switching to another coordinate subset. Extensive evaluations show that CobBO finds solutions comparable to or better than other state-of-the-art methods for dimensions ranging from tens to hundreds, while reducing the trial complexity.

XNAS: Neural Architecture Search with Expert Advice

This paper introduces a novel optimization method for differential neural architecture search, based on the theory of prediction with expert advice. Its optimization criterion is well fitted for an architecture-selection, i.e., it minimizes the regret incurred by a sub-optimal selection of operations. Unlike previous search relaxations, that require hard pruning of architectures, our method is designed to dynamically wipe out inferior architectures and enhance superior ones. It achieves an optimal worst-case regret bound and suggests the use of multiple learning-rates, based on the amount of information carried by the backward gradients. Experiments show that our algorithm achieves a strong performance over several image classification datasets. Specifically, it obtains an error rate of 1.6% for CIFAR-10, 24% for ImageNet under mobile settings, and achieves state-of-the-art results on three additional datasets.

ASAP: Architecture Search, Anneal and Prune

Automatic methods for Neural Architecture Search (NAS) have been shown to produce state-of-the-art network models, yet, their main drawback is the computational complexity of the search process. As some primal methods optimized over a discrete search space, thousands of days of GPU were required for convergence. A recent approach is based on constructing a differentiable search space that enables gradient-based optimization, thus reducing the search time to a few days. While successful, such methods still include some incontinuous steps, e.g., the pruning of many weak connections at once. In this paper, we propose a differentiable search space that allows the annealing of architecture weights, while gradually pruning inferior operations, thus the search converges to a single output network in a continuous manner. Experiments on several vision datasets demonstrate the effectiveness of our method with respect to the search cost, accuracy and the memory footprint of the achieved model.