Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Projection Algorithm for the Unitary Weights
59
0
0.0
(
0
)
Added by
Hao-Yuan Chang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Authors
Hao-Yuan Chang
Ask ChatGPT about the research
No Arabic abstract
Unitary neural networks are promising alternatives for solving the exploding and vanishing activation/gradient problem without the need for explicit normalization that reduces the inference speed. However, they often require longer training time due to the additional unitary constraints on their weight matrices. Here we show a novel algorithm using a backpropagation technique with Lie algebra for computing approximated unitary weights from their pre-trained, non-unitary counterparts. The unitary networks initialized with these approximations can reach the desired accuracies much faster, mitigating their training time penalties while maintaining inference speedups. Our approach will be instrumental in the adaptation of unitary networks, especially for those neural architectures where pre-trained weights are freely available.
rate research
Read More
How much credit (or blame) should an action taken in a state get for a future reward? This is the fundamental temporal credit assignment problem in Reinforcement Learning (RL). One of the earliest and still most widely used heuristics is to assign this credit based on a scalar coefficient $lambda$ (treated as a hyperparameter) raised to the power of the time interval between the state-action and the reward. In this empirical paper, we explore heuristics based on more general pairwise weightings that are functions of the state in which the action was taken, the state at the time of the reward, as well as the time interval between the two. Of course it isnt clear what these pairwise weight functions should be, and because they are too complex to be treated as hyperparameters we develop a metagradient procedure for learning these weight functions during the usual RL training of a policy. Our empirical work shows that it is often possible to learn these pairwise weight functions during learning of the policy to achieve better performance than competing approaches.
Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computationally hard (under cryptographic assumptions), and practitioners typically resort to search heuristics which suffer from the usual local optima issues. We prove that under a natural separation condition (bounds on the smallest singular value of the HMM parameters), there is an efficient and provably correct algorithm for learning HMMs. The sample complexity of the algorithm does not explicitly depend on the number of distinct (discrete) observations---it implicitly depends on this quantity through spectral properties of the underlying HMM. This makes the algorithm particularly applicable to settings with a large number of observations, such as those in natural language processing where the space of observation is sometimes the words in a language. The algorithm is also simple, employing only a singular value decomposition and matrix multiplications.
In this paper, we briefly review the basic scheme of the pseudoinverse learning (PIL) algorithm and present some discussions on the PIL, as well as its variants. The PIL algorithm, first presented in 1995, is a non-gradient descent and non-iterative learning algorithm for multi-layer neural networks and has several advantages compared with gradient descent based algorithms. Some new viewpoints to PIL algorithm are presented, and several common pitfalls in practical implementation of the neural network learning task are also addressed. In addition, we show that so called extreme learning machine is a Variant crEated by Simple name alTernation (VEST) of the PIL algorithm for single hidden layer feedforward neural networks.
Gradient-based algorithms for training ResNets typically require a forward pass of the input data, followed by back-propagating the objective gradient to update parameters, which are time-consuming for deep ResNets. To break the dependencies between modules in both the forward and backward modes, auxiliary-variable methods such as the penalty and augmented Lagrangian (AL) approaches have attracted much interest lately due to their ability to exploit layer-wise parallelism. However, we observe that large communication overhead and lacking data augmentation are two key challenges of these methods, which may lead to low speedup ratio and accuracy drop across multiple compute devices. Inspired by the optimal control formulation of ResNets, we propose a novel serial-parallel hybrid training strategy to enable the use of data augmentation, together with downsampling filters to reduce the communication cost. The proposed strategy first trains the network parameters by solving a succession of independent sub-problems in parallel and then corrects the network parameters through a full serial forward-backward propagation of data. Such a strategy can be applied to most of the existing layer-parallel training methods using auxiliary variables. As an example, we validate the proposed strategy using penalty and AL methods on ResNet and WideResNet across MNIST, CIFAR-10 and CIFAR-100 datasets, achieving significant speedup over the traditional layer-serial training methods while maintaining comparable accuracy.
With the recent evolution of mobile health technologies, health scientists are increasingly interested in developing just-in-time adaptive interventions (JITAIs), typically delivered via notification on mobile device and designed to help the user prevent negative health outcomes and promote the adoption and maintenance of healthy behaviors. A JITAI involves a sequence of decision rules (i.e., treatment policy) that takes the users current context as input and specifies whether and what type of an intervention should be provided at the moment. In this paper, we develop a Reinforcement Learning (RL) algorithm that continuously learns and improves the treatment policy embedded in the JITAI as the data is being collected from the user. This work is motivated by our collaboration on designing the RL algorithm in HeartSteps V2 based on data from HeartSteps V1. HeartSteps is a physical activity mobile health application. The RL algorithm developed in this paper is being used in HeartSteps V2 to decide, five times per day, whether to deliver a context-tailored activity suggestion.
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
