اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدDecoupling Gating from Linearity
59
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
ReLU neural-networks have been in the focus of many recent theoretical works, trying to explain their empirical success. Nonetheless, there is still a gap between current theoretical results and empirical observations, even in the case of shallow (one hidden-layer) networks. For example, in the task of memorizing a random sample of size $m$ and dimension $d$, the best theoretical result requires the size of the network to be $tilde{Omega}(frac{m^2}{d})$, while empirically a network of size slightly larger than $frac{m}{d}$ is sufficient. To bridge this gap, we turn to study a simplified model for ReLU networks. We observe that a ReLU neuron is a product of a linear function with a gate (the latter determines whether the neuron is active or not), where both share a jointly trained weight vector. In this spirit, we introduce the Gated Linear Unit (GaLU), which simply decouples the linearity from the gating by assigning different vectors for each role. We show that GaLU networks allow us to get optimization and generalization results that are much stronger than those available for ReLU networks. Specifically, we show a memorization result for networks of size $tilde{Omega}(frac{m}{d})$, and improved generalization bounds. Finally, we show that in some scenarios, GaLU networks behave similarly to ReLU networks, hence proving to be a good choice of a simplified model.
قيم البحث
اقرأ أيضاً
What makes untrained deep neural networks (DNNs) different from the trained performant ones? By zooming into the weights in well-trained DNNs, we found it is the location of weights that hold most of the information encoded by the training. Motivated
by this observation, we hypothesize that weights in stochastic gradient-based method trained DNNs can be separated into two dimensions: the locations of weights and their exact values. To assess our hypothesis, we propose a novel method named Lookahead Permutation (LaPerm) to train DNNs by reconnecting the weights. We empirically demonstrate the versatility of LaPerm while producing extensive evidence to support our hypothesis: when the initial weights are random and dense, our method demonstrates speed and performance similar to or better than that of regular optimizers, e.g., Adam; when the initial weights are random and sparse (many zeros), our method changes the way neurons connect and reach accuracy comparable to that of a well-trained fully initialized network; when the initial weights share a single value, our method finds weight agnostic neural network with far better-than-chance accuracy.
This paper challenges the common assumption that the weight $beta$, in $beta$-VAE, should be larger than $1$ in order to effectively disentangle latent factors. We demonstrate that $beta$-VAE, with $beta < 1$, can not only attain good disentanglement
but also significantly improve reconstruction accuracy via dynamic control. The paper removes the inherent trade-off between reconstruction accuracy and disentanglement for $beta$-VAE. Existing methods, such as $beta$-VAE and FactorVAE, assign a large weight to the KL-divergence term in the objective function, leading to high reconstruction errors for the sake of better disentanglement. To mitigate this problem, a ControlVAE has recently been developed that dynamically tunes the KL-divergence weight in an attempt to control the trade-off to more a favorable point. However, ControlVAE fails to eliminate the conflict between the need for a large $beta$ (for disentanglement) and the need for a small $beta$. Instead, we propose DynamicVAE that maintains a different $beta$ at different stages of training, thereby decoupling disentanglement and reconstruction accuracy. In order to evolve the weight, $beta$, along a trajectory that enables such decoupling, DynamicVAE leverages a modified incremental PI (proportional-integral) controller, and employs a moving average as well as a hybrid annealing method to evolve the value of KL-divergence smoothly in a tightly controlled fashion. We theoretically prove the stability of the proposed approach. Evaluation results on three benchmark datasets demonstrate that DynamicVAE significantly improves the reconstruction accuracy while achieving disentanglement comparable to the best of existing methods. The results verify that our method can separate disentangled representation learning and reconstruction, removing the inherent tension between the two.
The goal of this work is to shed light on the remarkable phenomenon of transition to linearity of certain neural networks as their width approaches infinity. We show that the transition to linearity of the model and, equivalently, constancy of the (n
eural) tangent kernel (NTK) result from the scaling properties of the norm of the Hessian matrix of the network as a function of the network width. We present a general framework for understanding the constancy of the tangent kernel via Hessian scaling applicable to the standard classes of neural networks. Our analysis provides a new perspective on the phenomenon of constant tangent kernel, which is different from the widely accepted lazy training. Furthermore, we show that the transition to linearity is not a general property of wide neural networks and does not hold when the last layer of the network is non-linear. It is also not necessary for successful optimization by gradient descent.
Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs. Most GNNs follow a message-passing scheme where the node representations are updated by aggregating and transforming
the information from the neighborhood. Meanwhile, they adopt the same strategy in aggregating the information from different feature dimensions. However, suggested by social dimension theory and spectral embedding, there are potential benefits to treat the dimensions differently during the aggregation process. In this work, we investigate to enable heterogeneous contributions of feature dimensions in GNNs. In particular, we propose a general graph feature gating network (GFGN) based on the graph signal denoising problem and then correspondingly introduce three graph filters under GFGN to allow different levels of contributions from feature dimensions. Extensive experiments on various real-world datasets demonstrate the effectiveness and robustness of the proposed frameworks.
Reinforcement learning (RL) is one of the most active fields of AI research. Despite the interest demonstrated by the research community in reinforcement learning, the development methodology still lags behind, with a severe lack of standard APIs to
foster the development of RL applications. OpenAI Gym is probably the most used environment to develop RL applications and simulations, but most of the abstractions proposed in such a framework are still assuming a semi-structured methodology. This is particularly relevant for agent-based models whose purpose is to analyse adaptive behaviour displayed by self-learning agents in the simulation. In order to bridge this gap, we present a workflow and tools for the decoupled development and maintenance of multi-purpose agent-based models and derived single-purpose reinforcement learning environments, enabling the researcher to swap out environments with ones representing different perspectives or different reward models, all while keeping the underlying domain model intact and separate. The Sim-Env Python library generates OpenAI-Gym-compatible reinforcement learning environments that use existing or purposely created domain models as their simulation back-ends. Its design emphasizes ease-of-use, modularity and code separation.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
