The specifick-nn probability model is described in Eq. (7) of Garnett et al. (2012) (line 327). The only modification needed to adaptENSto the cost-sensitivesetting is appropriately specifying the "budget," as15 described lines 258-265 in the main text. Again,wedisagree.Wehave26 compared with both the most relevant work on activesearch (Garnett, etal.

This paper introduces FSL-HDnn, an energy-efficient accelerator that implements the end-to-end pipeline of feature extraction, classification, and on-chip few-shot learning (FSL) through gradient-free learning techniques in a 40 nm CMOS process. At its core, FSL-HDnn integrates two low-power modules: Weight clustering feature extractor and Hyperdimensional Computing (HDC). Feature extractor utilizes advanced weight clustering and pattern reuse strategies for optimized CNN-based feature extraction. Meanwhile, HDC emerges as a novel approach for lightweight FSL classifier, employing hyperdimensional vectors to improve training accuracy significantly compared to traditional distance-based approaches. This dual-module synergy not only simplifies the learning process by eliminating the need for complex gradients but also dramatically enhances energy efficiency and performance. Specifically, FSL-HDnn achieves an Intensity unprecedented energy efficiency of 5.7 TOPS/W for feature 1 extraction and 0.78 TOPS/W for classification and learning Training Intensity phases, achieving improvements of 2.6X and 6.6X, respectively, Storage over current state-of-the-art CNN and FSL processors.

Knowing the learning dynamics of policy is significant to unveiling the mysteries of Reinforcement Learning (RL). It is especially crucial yet challenging to Deep RL, from which the remedies to notorious issues like sample inefficiency and learning instability could be obtained. In this paper, we study how the policy networks of typical DRL agents evolve during the learning process by empirically investigating several kinds of temporal change for each policy parameter. On typical MuJoCo and DeepMind Control Suite (DMC) benchmarks, we find common phenomena for TD3 and RAD agents: 1) the activity of policy network parameters is highly asymmetric and policy networks advance monotonically along very few major parameter directions; 2) severe detours occur in parameter update and harmonic-like changes are observed for all minor parameter directions. By performing a novel temporal SVD along policy learning path, the major and minor parameter directions are identified as the columns of right unitary matrix associated with dominant and insignificant singular values respectively. Driven by the discoveries above, we propose a simple and effective method, called Policy Path Trimming and Boosting (PPTB), as a general plug-in improvement to DRL algorithms. The key idea of PPTB is to periodically trim the policy learning path by canceling the policy updates in minor parameter directions, while boost the learning path by encouraging the advance in major directions. In experiments, we demonstrate the general and significant performance improvements brought by PPTB, when combined with TD3 and RAD in MuJoCo and DMC environments respectively.

Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the pruned filters is completely dropped. To utilize the trained pruned filters, we proposed a SofteR Filter Pruning (SRFP) method and its variant, Asymptotic SofteR Filter Pruning (ASRFP), simply decaying the pruned weights with a monotonic decreasing parameter. Our methods perform well across various networks, datasets and pruning rates, also transferable to weight pruning. On ILSVRC-2012, ASRFP prunes 40% of the parameters on ResNet-34 with 1.63% top-1 and 0.68% top-5 accuracy improvement. In theory, SRFP and ASRFP are an incremental regularization of the pruned filters. Besides, We note that SRFP and ASRFP pursue better results while slowing down the speed of convergence.

In distributed deep learning, a large batch size in Stochastic Gradient Descent is required to fully exploit the computing power in distributed systems. However, generalization gap (accuracy loss) was observed because large-batch training converges to sharp minima which have bad generalization [1][2]. This contradiction hinders the scalability of distributed deep learning. We propose SmoothOut to smooth out sharp minima in Deep Neural Networks (DNNs) and thereby close generalization gap. SmoothOut perturbs multiple copies of the DNN in the parameter space and averages these copies. We prove that SmoothOut can eliminate sharp minima. Perturbing and training multiple DNN copies is inefficient, we propose a stochastic version of SmoothOut which only introduces overhead of noise injection and denoising per iteration. We prove that the Stochastic SmoothOut is an unbiased approximation of the original SmoothOut. In experiments on a variety of DNNs and datasets, SmoothOut consistently closes generalization gap in large-batch training within the same epochs. Moreover, SmoothOut can guide small-batch training to flatter minima and improve generalization. Our source code is in https://github.com/wenwei202/smoothout