A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Gradient Gating improves deep GNNs by modulating message passing updates.
DG improves policy gradient efficiency by selectively backpropagating only valuable samples.
Long Short-Term Memory (LSTM) infers the long term dependency through a cell state maintained by the input and the forget gate structures, which models a gate output as a value in [0,1] through a sigmoid function. However, due to the graduality of the sigmoid function, the sigmoid gate is not flexible in representing m…
A new method for differentiable structured sparsity improves neural network performance and sparsity.
LSTMs were introduced to combat vanishing gradients in simple RNNs by augmenting them with gated additive recurrent connections. We present an alternative view to explain the success of LSTMs: the gates themselves are versatile recurrent models that provide more representational power than previously appreciated. We do…
Study reveals biases in gradient descent for GLNs, improving neural network performance.
Improved GNN handles long-range dependencies in multi-relational graphs.
Gating is a key feature in modern neural networks including LSTMs, GRUs and sparsely-gated deep neural networks. The backbone of such gated networks is a mixture-of-experts layer, where several experts make regression decisions and gating controls how to weigh the decisions in an input-dependent manner. Despite having …
Recurrent neural networks can be difficult to train on long sequence data due to the well-known vanishing gradient problem. Some architectures incorporate methods to reduce RNN state updates, therefore allowing the network to preserve memory over long temporal intervals. To address these problems of convergence, this p…
DSelect-k improves MoE models for multi-task learning with better performance and smoother training.
We introduce the Genetic-Gated Networks (G2Ns), simple neural networks that combine a gate vector composed of binary genetic genes in the hidden layer(s) of networks. Our method can take both advantages of gradient-free optimization and gradient-based optimization methods, of which the former is effective for problems …
New interpretation of RNN forget gate improves learnability for long-term sequential data.
In order to quantize the gate parameters of the LSTM (Long Short-Term Memory) neural network model with almost no recognition performance degraded, a new quantization method named Quantization Loss Re-Learn Method is proposed in this paper. The method does lossy quantization on gate parameters during training iteration…
Successful recurrent models such as long short-term memories (LSTMs) and gated recurrent units (GRUs) use ad hoc gating mechanisms. Empirically these models have been found to improve the learning of medium to long term temporal dependencies and to help with vanishing gradient issues. We prove that learnable gates in a…
A major contributing factor to the recent advances in deep neural networks is structural units that let sensory information and gradients to propagate easily. Gating is one such structure that acts as a flow control. Gates are employed in many recent state-of-the-art recurrent models such as LSTM and GRU, and feedforwa…
A simple gating mechanism improves deep learning convergence.
Recurrent neural networks (RNNs) are powerful dynamical models for data with complex temporal structure. However, training RNNs has traditionally proved challenging due to exploding or vanishing of gradients. RNN models such as LSTMs and GRUs (and their variants) significantly mitigate these issues associated with trai…
Understanding the role of (stochastic) gradient descent (SGD) in the training and generalisation of deep neural networks (DNNs) with ReLU activation has been the object study in the recent past. In this paper, we make use of deep gated networks (DGNs) as a framework to obtain insights about DNNs with ReLU activation. I…
New algorithm trains ReLU gates provably in linear time.
Architecture optimization, which is a technique for finding an efficient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difficu…
Methods from convex optimization are widely used as building blocks for deep learning algorithms. However, the reasons for their empirical success are unclear, since modern convolutional networks (convnets), incorporating rectifier units and max-pooling, are neither smooth nor convex. Standard guarantees therefore do n…
DG separates successes and failures by gating updates with advantage and surprisal.
FleXOR trains fractional quantization for neural networks, improving accuracy and size.
A new method prunes neural networks efficiently without losing effectiveness.
We propose a practical method for norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC and BIC, well-known …
A framework for modular training of robust generative models.
Recurrent Neural Networks (RNNs) play a major role in the field of sequential learning, and have outperformed traditional algorithms on many benchmarks. Training deep RNNs still remains a challenge, and most of the state-of-the-art models are structured with a transition depth of 2-4 layers. Recurrent Highway Networks …
New model optimizes portfolios with realistic transaction costs.
This work connects neural network training to convex optimization via the NTK.
Federated Learning with L0 constraint improves sparsity and performance.
The paper studies 4-qubit Clifford states and their properties.
Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an even longer training process with iterative pruning and retraining. We observe t…
Improved logistic MoE with sigmoid gate shows better sample efficiency.
New method prepares 3-qubit states using local gates and controlled-Z gates.
Gradient-free method improves predictive accuracy for probabilistic models.
Sigmoid gating is more sample efficient than softmax in mixture of experts.
In quantum computation, series of quantum gates have to be arranged in a predefined sequence that led to a quantum circuit in order to solve a particular problem. What if the sequence of quantum gates is known but both the problem to be solved and the outcome of the so defined quantum circuit remain in the shadow? This…
Bayesian Bits unifies quantization and pruning through gradient optimization.
Gated attention improves model curvature, enhancing performance on nonlinear tasks.
Gated attention improves performance by using a hierarchical mixture of experts.
Given the success of the gated recurrent unit, a natural question is whether all the gates of the long short-term memory (LSTM) network are necessary. Previous research has shown that the forget gate is one of the most important gates in the LSTM. Here we show that a forget-gate-only version of the LSTM with chrono-ini…
Improved HMoE models using Laplace gating function enhance expert specialization and performance.
We discuss an autoencoder model in which the encoding and decoding functions are implemented by decision trees. We use the soft decision tree where internal nodes realize soft multivariate splits given by a gating function and the overall output is the average of all leaves weighted by the gating values on their path. …
The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNN) by reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while…
New algorithm improves on EM for streaming data, outperforming existing methods.
This study analyzes communication constraints in MoE architectures using information theory.
Introduces Causal Energy Minimization to understand Transformer layers.
Bayesian methods have been successfully applied to sparsify weights of neural networks and to remove structure units from the networks, e. g. neurons. We apply and further develop this approach for gated recurrent architectures. Specifically, in addition to sparsification of individual weights and neurons, we propose t…