Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet fail to efficiently represent and execute such neural networks, due to lack of s…
On-device research index
arXiv research
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Recursive Neural Networks”
The paper uses tensor decompositions to improve neural network models for tree data.
problem Encoding structural knowledge from tree-structured data efficiently.
method Introduces new aggregation functions using Canonical and Tensor-Train decompositions.
result Proposed models outperform traditional methods on tree classification tasks.
Recurrent neural networks (RNNs) process input text sequentially and model the conditional transition between word tokens. In contrast, the advantages of recursive networks include that they explicitly model the compositionality and the recursive structure of natural language. However, the current recursive architectur…
Recursive KalmanNet combines neural networks with Kalman filters for precise state estimation.
problem State estimation in systems with noisy measurements and non-Gaussian noise.
method Recursive KalmanNet uses a recurrent neural network to estimate states with consistent error covariance, optimizing for Gaussian negative log-likelihood.
result Recursive KalmanNet outperforms conventional Kalman filters and deep learning-based estimators in non-Gaussian noise conditions.
While it has become common to perform automated translations on natural language, performing translations between different representations of mathematical formulae has thus far not been possible. We implemented the first translator for mathematical formulae based on recursive neural networks. We chose recursive neural…
In a recurrent setting, conventional approaches to neural architecture search find and fix a general model for all data samples and time steps. We propose a novel algorithm that can dynamically search for the structure of cells in a recurrent neural network model. Based on a combination of recurrent and recursive neura…
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates…
Recently, deep architectures, such as recurrent and recursive neural networks have been successfully applied to various natural language processing tasks. Inspired by bidirectional recurrent neural networks which use representations that summarize the past and future around an instance, we propose a novel architecture …
This paper extends geometric study of neural networks to non-differentiable layers and random walks.
problem Understanding the geometric properties of neural networks, especially those with non-differentiable activation functions.
method Singular Riemannian geometry approach to convolutional, residual, and recursive neural networks.
result Illustrated geometric findings with numerical experiments on image classification and thermodynamic problems.
This paper reviews graph convolutional neural networks (GCNNs) through the lens of edge-variant graph filters. The edge-variant graph filter is a finite order, linear, and local recursion that allows each node, in each iteration, to weigh differently the information of its neighbors. By exploiting this recursion, we fo…
This work presents an explicit-implicit procedure to compute a model predictive control (MPC) law with guarantees on recursive feasibility and asymptotic stability. The approach combines an offline-trained fully-connected neural network with an online primal active set solver. The neural network provides a control inpu…
ERM uses energy-based selection to improve recursive reasoning.
problem Lack of principled inference mechanism in recursive models.
method Energy-guided Recursive Model (ERM) introduces Hopfield energies for trajectory selection.
result ERM achieves optimal solutions on various puzzles.
Since the machine learning techniques are improving rapidly, it has been shown that the image recognition techniques in deep neural networks can be used to detect jet substructure. And it turns out that deep neural networks can match or outperform traditional approach of expert features. However, there are disadvantage…
Deep learning solves dynamic programming with recursive utility.
problem Challenges in solving high-dimensional discrete-time dynamic programming problems with recursive utility.
method Certainty Equivalent Learning (CEL) algorithm that learns certainty-equivalent value directly with neural networks.
result Accurate value and policy approximations in high-dimensional problems, comparable to VFI in some cases.
Recursive KalmanNet generalizes well in noisy, out-of-distribution scenarios.
problem Generalization in noisy, out-of-distribution scenarios.
method Recurrent neural network guided by a Kalman filter.
result Recursive KalmanNet performs well in scenarios with different temporal dynamics from training data.
Recent progress in applying machine learning for jet physics has been built upon an analogy between calorimeters and images. In this work, we present a novel class of recursive neural networks built instead upon an analogy between QCD and natural languages. In the analogy, four-momenta are like words and the clustering…
Study eigenvalue distributions of neural kernels for linear-width networks.
problem Eigenvalue distributions of neural kernels in linear-width networks.
method Asymptotic analysis of Conjugate Kernel and Neural Tangent Kernel under random initialization and approximate orthogonality.
result Eigenvalue distributions converge to deterministic limits, described by recursive fixed-point equations.
Greedy training of recursive partitioning estimators faces a computational barrier when the true function doesn't satisfy a specific property.
problem Computational inefficiency of greedy training for recursive partitioning estimators.
method Analysis of greedy training for sparse regression functions over binary features.
result Greedy training requires exponential samples when the true function doesn't satisfy a specific property (MSP), but only logarithmic samples when it does.
The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to adversarial attacks. In this paper, we propose a recursive algorithm, RecurJac, to comput…
Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science. Quantum-chemical simulations such as density functional theory (DFT) have been widely used for calculating the molecule properties, however, because of the heavy computational cost, it is difficult to search a…
A new algorithm for learning shallow neural networks with infinite width.
problem Learning shallow over-parameterized neural networks.
method Sinkhorn proximal algorithm approximating mean field learning dynamics.
result The algorithm performs gradient descent of the free energy associated with the risk functional.
Score-based martingale posteriors improve uncertainty quantification in deep neural networks.
problem Uncertainty quantification in deep neural networks
method Score-based martingale posteriors
result SMPs provide a fast, deterministic way to simulate the limiting random variable.
CEFOL uses deep learning for dynamic programming with recursive utility.
problem Challenges in solving dynamic programming problems with recursive utility.
method Introduces a separate neural network for certainty equivalent, uses first-order optimality conditions to learn value and policy functions.
result CEFOL achieves high accuracy in learning value and policy functions, matching VFI benchmarks.
Emergence in non-neural models: grokking modular arithmetic via average gradient outer productstat.ML
Recursive Feature Machines show grokking in modular arithmetic without neural networks.
problem Grokking in modular arithmetic tasks.
method Recursive Feature Machines (RFM) with Average Gradient Outer Product (AGOP).
result RFM and neural networks learn block-circulant features to solve modular arithmetic.
ThriftyNet uses a single convolutional layer recursively to maximize parameter usage.
problem Maximizing the use of parameters in deep convolutional neural networks.
method A single convolutional layer is used recursively, with normalization, non-linearities, downsampling, and shortcuts to maintain model expressivity.
result ThriftyNet achieves competitive performance with significantly fewer parameters.
Paper identifies how neural networks learn features.
problem Understanding how neural networks automatically select features.
method Deep Neural Feature Ansatz, implementing average gradient outer product.
result Recursive Feature Machines achieve state-of-the-art performance.
Symmetry in neural networks affects generalization, as shown by CLT and RG transformations.
problem Improving generalization in neural networks by incorporating physical symmetries.
method Evaluation of symmetry constraints and expressivity in MLPs and GNNs using the CLT as a test case.
result Overly complex or overconstrained models generalize poorly, revealing a competition between symmetry constraints and expressivity.
Combines neural networks with splitting-up method for filtering equations.
problem Approximating the solution of filtering equations for signal processes.
method Combines splitting-up method with neural networks.
result Produces an approximation of the unnormalised conditional distribution.
Modern machine learning techniques, such as convolutional, recurrent and recursive neural networks, have shown promise for jet substructure at the Large Hadron Collider. For example, they have demonstrated effectiveness at boosted top or W boson identification or for quark/gluon discrimination. We explore these methods…
The study examines neural networks with random weights and biases, finding that depth-to-width ratio controls fluctuations and correlations.
problem Exploring the exploding and vanishing gradient problem in neural networks with random weights and biases.
method Sharp estimates of joint cumulants and solving cumulant recursions in powers of 1/n.
result The depth-to-width ratio plays a crucial role in controlling fluctuations and correlations, leading to the occurrence of exploding and vanishing gradients.
Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learningcs.LG
In this paper, we study the problem of node representation learning with graph neural networks. We present a graph neural network class named recurrent graph neural network (RGNN), that address the shortcomings of prior methods. By using recurrent units to capture the long-term dependency across layers, our methods can…
Echo State Networks (ESN) are a class of Recurrent Neural Networks (RNN) that has gained substantial popularity due to their effectiveness, ease of use and potential for compact hardware implementation. An ESN contains the three network layers input, reservoir and readout where the reservoir is the truly recurrent netw…
We present a framework to derive upper bounds on the number of regions that feed-forward neural networks with ReLU activation functions are affine linear on. It is based on an inductive analysis that keeps track of the number of such regions per dimensionality of their images within the layers. More precisely, the info…
Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation, the workhorse for training these networks, is an inherently sequential process that is difficult t…
Constructs classifiers for neural networks with specific data configurations.
problem Finding global minima of deep ReLU neural networks on sequentially separable data.
method Explicitly constructs zero loss neural network classifiers using cumulative parameters and truncation maps.
result Global minimizers can be described with a limited number of parameters based on the data structure.
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks? This paper introduces stochastic recurrent neural networks which glue a deterministic recurrent neural network and a state space model together to form a stochastic and sequential neural generative model. The c…
New framework for DNN training guarantees convergence to global minimum.
problem Training deep neural networks to converge to global minimum.
method Reformulated minimization problem with recursive algorithmic framework, using bounded style assumptions.
result Convergence to an ε-(global) minimum with O(1/ε^3) gradient computations.
AGOP mechanism explains deep neural collapse in neural networks.
problem Explaining the rigid structure of data representations in deep neural networks.
method Introducing AGOP and Deep RFM to demonstrate DNC.
result AGOP mechanism causes deep neural collapse in neural networks.
Paper presents a neural network method for efficient xVA computation and risk management.
problem High-dimensional counterparty credit risk valuation and management.
method Neural network-based BSDE solver for coupled system of BSDEs for xVA.
result Efficient computation of xVA for high-dimensional portfolios.
Tab-TRM uses recursive model for insurance pricing on tabular data.
problem Insurance pricing on tabular data.
method Adapts recursive latent reasoning to insurance modeling using a compact, parameter-efficient network.
result Improves insurance pricing accuracy using iterative refinement of latent tokens.
Using deep neural networks for identifying physics objects at the Large Hadron Collider (LHC) has become a powerful alternative approach in recent years. After successful training of deep neural networks, examining the trained networks not only helps us understand the behaviour of neural networks, but also helps improv…
Synthesizing programs using example input/outputs is a classic problem in artificial intelligence. We present a method for solving Programming By Example (PBE) problems by using a neural model to guide the search of a constraint logic programming system called miniKanren. Crucially, the neural model uses miniKanren's i…
New approach detects sensitive info in text, outperforming previous methods.
problem Detecting sensitive information in unstructured text documents.
method Developed novel recursive neural network approaches for sensitive info detection, assuming only labeled examples.
result Our approaches significantly outperform previous keyword-based methods on real-world data.
Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic…
INEUS solves high-dimensional PIDEs efficiently with neural networks.
problem Solving high-dimensional partial integro-differential equations (PIDEs) efficiently.
method INEUS uses iterative neural networks to replace nonlocal integrals with sampling and reformulates PIDE solving as recursive regression.
result INEUS delivers accurate and scalable solutions for high-dimensional linear and nonlinear PIDEs.
Stock selection improved with a novel neural model capturing continuous stock dynamics.
problem Lack of continuous stock dynamics prediction and implicit cross-domain dependencies.
method StockODE, a latent variable model with NRODEs and hierarchical hypergraph for continuous stock volatility and inter-domain dependencies.
result Significantly outperforms baselines, improving Sharpe Ratio by up to 18.57%.
Implicit deep learning prediction rules generalize the recursive rules of feedforward neural networks. Such rules are based on the solution of a fixed-point equation involving a single vector of hidden features, which is thus only implicitly defined. The implicit framework greatly simplifies the notation of deep learni…
Motivated by the flexibility of biological neural networks whose connectivity structure changes significantly during their lifetime, we introduce the Unstructured Recursive Network (URN) and demonstrate that it can exhibit similar flexibility during training via gradient descent. We show empirically that many of the di…