Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAdaSwarm: Augmenting Gradient-Based optimizers in Deep Learning with Swarm Intelligence
98
0
0.0
(
0
)
Added by
Snehanshu Saha
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper introduces AdaSwarm, a novel gradient-free optimizer which has similar or even better performance than the Adam optimizer adopted in neural networks. In order to support our proposed AdaSwarm, a novel Exponentially weighted Momentum Particle Swarm Optimizer (EMPSO), is proposed. The ability of AdaSwarm to tackle optimization problems is attributed to its capability to perform good gradient approximations. We show that, the gradient of any function, differentiable or not, can be approximated by using the parameters of EMPSO. This is a novel technique to simulate GD which lies at the boundary between numerical methods and swarm intelligence. Mathematical proofs of the gradient approximation produced are also provided. AdaSwarm competes closely with several state-of-the-art (SOTA) optimizers. We also show that AdaSwarm is able to handle a variety of loss functions during backpropagation, including the maximum absolute error (MAE).
rate research
Read More
Swarm intelligence is the collective behavior emerging in systems with locally interacting components. Because of their self-organization capabilities, swarm-based systems show essential properties for handling real-world problems such as robustness, scalability, and flexibility. Yet, we do not know why swarm-based algorithms work well and neither we can compare the different approaches in the literature. The lack of a common framework capable of characterizing these several swarm-based algorithms, transcending their particularities, has led to a stream of publications inspired by different aspects of nature without a systematic comparison over existing approaches. Here, we address this gap by introducing a network-based framework---the interaction network---to examine computational swarm-based systems via the optics of the social dynamics of such interaction network; a clear example of network science being applied to bring further clarity to a complicated field within artificial intelligence. We discuss the social interactions of four well-known swarm-based algorithms and provide an in-depth case study of the Particle Swarm Optimization. The interaction network enables researchers to study swarm algorithms as systems, removing the algorithm particularities from the analyses while focusing on the structure of the social interactions.
Many applications in machine learning require optimizing a function whose true gradient is unknown, but where surrogate gradient information (directions that may be correlated with, but not necessarily identical to, the true gradient) is available instead. This arises when an approximate gradient is easier to compute than the full gradient (e.g. in meta-learning or unrolled optimization), or when a true gradient is intractable and is replaced with a surrogate (e.g. in certain reinforcement learning applications, or when using synthetic gradients). We propose Guided Evolutionary Strategies, a method for optimally using surrogate gradient directions along with random search. We define a search distribution for evolutionary strategies that is elongated along a guiding subspace spanned by the surrogate gradients. This allows us to estimate a descent direction which can then be passed to a first-order optimizer. We analytically and numerically characterize the tradeoffs that result from tuning how strongly the search distribution is stretched along the guiding subspace, and we use this to derive a setting of the hyperparameters that works well across problems. Finally, we apply our method to example problems, demonstrating an improvement over both standard evolutionary strategies and first-order methods (that directly follow the surrogate gradient). We provide a demo of Guided ES at https://github.com/brain-research/guided-evolutionary-strategies
Algorithms implementing populations of agents which interact with one another and sense their environment may exhibit emergent behavior such as self-organization and swarm intelligence. Here a swarm system, called Databionic swarm (DBS), is introduced which is able to adapt itself to structures of high-dimensional data characterized by distance and/or density-based structures in the data space. By exploiting the interrelations of swarm intelligence, self-organization and emergence, DBS serves as an alternative approach to the optimization of a global objective function in the task of clustering. The swarm omits the usage of a global objective function and is parameter-free because it searches for the Nash equilibrium during its annealing process. To our knowledge, DBS is the first swarm combining these approaches. Its clustering can outperform common clustering methods such as K-means, PAM, single linkage, spectral clustering, model-based clustering, and Ward, if no prior knowledge about the data is available. A central problem in clustering is the correct estimation of the number of clusters. This is addressed by a DBS visualization called topographic map which allows assessing the number of clusters. It is known that all clustering algorithms construct clusters, irrespective of the data set contains clusters or not. In contrast to most other clustering algorithms, the topographic map identifies, that clustering of the data is meaningless if the data contains no (natural) clusters. The performance of DBS is demonstrated on a set of benchmark data, which are constructed to pose difficult clustering problems and in two real-world applications.
When using deep, multi-layered architectures to build generative models of data, it is difficult to train all layers at once. We propose a layer-wise training procedure admitting a performance guarantee compared to the global optimum. It is based on an optimistic proxy of future performance, the best latent marginal. We interpret auto-encoders in this setting as generative models, by showing that they train a lower bound of this criterion. We test the new learning procedure against a state of the art method (stacked RBMs), and find it to improve performance. Both theory and experiments highlight the importance, when training deep architectures, of using an inference model (from data to hidden variables) richer than the generative model (from hidden variables to data).
As an emerging field, Automated Machine Learning (AutoML) aims to reduce or eliminate manual operations that require expertise in machine learning. In this paper, a graph-based architecture is employed to represent flexible combinations of ML models, which provides a large searching space compared to tree-based and stacking-based architectures. Based on this, an evolutionary algorithm is proposed to search for the best architecture, where the mutation and heredity operators are the key for architecture evolution. With Bayesian hyper-parameter optimization, the proposed approach can automate the workflow of machine learning. On the PMLB dataset, the proposed approach shows the state-of-the-art performance compared with TPOT, Autostacker, and auto-sklearn. Some of the optimized models are with complex structures which are difficult to obtain in manual design.
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
