Residual Neural Networks (ResNets) achieve state-of-the-art performance in many computer vision problems. Compared to plain networks without residual connections (PlnNets), ResNets train faster, generalize better, and suffer less from the so-called degradation problem. We introduce simplified (but still nonlinear) vers…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “simplified network”
Use simplified layerwise linear models to understand neural dynamics.
problem Complex neural network dynamics are hard to grasp.
method Apply simplified layerwise linear models to explain neural phenomena.
result Simplified models explain neural collapse, emergence, etc.
Deep learning using multi-layer neural networks (NNs) architecture manifests superb power in modern machine learning systems. The trained Deep Neural Networks (DNNs) are typically large. The question we would like to address is whether it is possible to simplify the NN during training process to achieve a reasonable pe…
Simplified neural network EFTs reveal a single critical condition.
problem Understanding neuron statistics in neural networks at initialization.
method Diagrammatic approach to effective field theories (EFTs).
result A single condition governs criticality of all neuron preactivations.
Simplified NAS for GNN architectures improves efficiency and expressiveness.
problem Efficient and effective discovery of optimal GNN architectures.
method SNAG framework with a novel search space and reinforcement learning.
result SNAG framework outperforms human-designed and existing NAS methods.
Simplifies neural network models by explicitly enforcing constraints in Cartesian coordinates.
problem Learning dynamics of complex systems efficiently and accurately.
method Embedding systems into Cartesian coordinates and using Lagrange multipliers to enforce constraints.
result Explicitly enforcing constraints leads to a 100x improvement in accuracy and data efficiency.
This paper studies how to compress neural networks while maintaining accuracy.
problem Compressing a two-layer neural network with fewer nodes without losing accuracy.
method Using tools from high-dimensional probability, the authors minimize the L_2 loss between the target and compressed networks.
result The error rate of the approximation is shown as a function of input dimension and network size in the mean-field limit.
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methodscs.LG
Simplifies convolutions using tensor networks and einsum for efficient second-order methods.
problem Complexity in analyzing and applying convolutions in deep learning.
method Viewing convolutions as tensor networks, drawing diagrams, and using einsum for efficient computation.
result Accelerates a KFAC variant up to 4.5x with reduced memory overhead.
DeepMimic trains neural networks using mostly unlabeled data.
problem Insufficient labeled data for deep learning.
method Mentor-Student approach with unlabeled data.
result Student model achieves mentor's performance without labeled data.
We sparsify gated RNNs by simplifying their structure.
problem Improving efficiency of RNNs by reducing their complexity.
method Adjust existing sparsification techniques to gated RNNs, sparsifying preactivations of gates.
result Simplified LSTM structure improves model performance and efficiency.
Fortuna simplifies uncertainty quantification in deep learning.
problem Improving uncertainty estimates in deep learning models.
method Supports various calibration techniques including conformal prediction and scalable Bayesian inference.
result Simplifies benchmarking and builds robust AI systems.
Finding optimal correction of errors in generic stabilizer codes is a computationally hard problem, even for simple noise models. While this task can be simplified for codes with some structure, such as topological stabilizer codes, developing good and efficient decoders still remains a challenge. In our work, we syste…
Neural network learns atomic coordinates from Patterson maps in a simplified case.
problem Training a neural network to infer atomic coordinates from Patterson maps.
method Synthetic data training, centering output maps, removing centrosymmetric inversion, and adding empty space.
result The network can generalize to infer atom positions from Patterson maps not in the training set.
Simplified LSTM models improve sentiment analysis on Twitter debate data.
problem Performing sentiment analysis on long sequence data from Twitter debates.
method Developed six parameter-reduced LSTM models (slim LSTM) for faster training and reduced computational cost.
result Slim LSTM models outperform standard LSTM model in sentiment analysis of GOP Debate Twitter dataset.
Deep ReLU networks can be simplified to a three-layer model.
problem Understanding the behavior of deep neural networks.
method Constructive proof and algorithm to transform deep networks into shallow ones.
result Deep ReLU networks can be represented by a simpler three-layer structure.
Paper studies simplified trisections and their equivalence classes.
problem Understanding right-left equivalence of simplified -trisections.
method Analyzes simplified trisection diagrams and upper-triangular handle-slides.
result At least two simplified -trisections can be right-left equivalent without being related by automorphisms or handle-slides.
This paper proposes a novel Stochastic Split Linearized Bregman Iteration (-LBI) algorithm to efficiently train the deep network. The -LBI introduces an iterative regularization path with structural sparsity. Our -LBI combines the computational efficiency of the LBI, and model selection consistency…
DASH simplifies neural networks for gene regulatory dynamics using domain knowledge.
problem Pruning neural networks for gene regulatory dynamics lacks biologically meaningful structure learning.
method DASH uses domain-specific structural information to guide network pruning, leading to sparser, better interpretable models.
result DASH outperforms general pruning methods in gene regulatory network inference, yielding deeper insights.
Improved model error correction online with neural networks in 4D-Var.
problem Reconstructing dynamics of imperfectly observed physical models.
method Weak-constraint 4D-Var framework with online neural network training.
result Online model error correction yields more accurate results than offline.
Neural networks can be simplified to linear regression for easier understanding by statisticians.
problem Introducing neural networks to statisticians who are not familiar with them.
method Describing neural networks that approximate linear regression and discussing customizations.
result Statisticians can now understand neural networks by focusing on linear regression.
Simplifies PLNNs to interpretable models for better explainability.
problem Challenges in interpretability of PLNNs for high-stakes applications.
method Trained deep network simplification and algorithm for reducing flat networks.
result Improved interpretability of PLNNs without sacrificing performance.
Random convolutional networks can be fooled with adversarial examples.
problem Existence of adversarial examples for random convolutional networks.
method Utilizing isoperimetric inequalities on the special orthogonal group .
result Adversarial examples exist for various random convolutional networks.
Recurrent neural networks with various types of hidden units have been used to solve a diverse range of problems involving sequence data. Two of the most recent proposals, gated recurrent units (GRU) and minimal gated units (MGU), have shown comparable promising results on example public datasets. In this paper, we int…
Improved hyperparameter optimization using simplified Transformer blocks.
problem Discovering optimal architectures in high-dimensional search spaces with limited exploration budgets.
method Simplified Transformer block for modeling hyper-parameter dependencies, actor-critic style algorithm, ensembling.
result Outperformed most algorithms on NAS-Bench-101 and Random Search in discovering more accurate model architectures.
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 ran…
No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with predictive networks. It is easy to implement and add to existing architectures, has…
We analyze neural collapse in neural networks, showing that features collapse to vertices of a Simplex ETF.
problem Understanding and optimizing the features learned in the last layer of neural networks during training.
method Simplified unconstrained feature model, studying the global optimization landscape of cross-entropy loss with weight decay.
result The global minimizers of the loss are Simplex ETFs, and other critical points are strict saddles with negative curvature.
EEGNN improves graph neural networks by enhancing graph structure.
problem Mis-simplification of graphs by removing self-loops and unweighted edges reduces GNN performance.
method Proposes EEGNN framework using DMPGM for better graph structural information.
result EEGNN achieves significant performance improvement over baselines.
Unified access package for fundamental physics datasets simplifies machine learning.
problem Lack of unified access to datasets from multiple fundamental physics disciplines.
method Unified Python package with common interface and reference models.
result Graph-based neural networks perform similarly to dedicated methods on various datasets.
Spatial blind source separation simplifies multivariate spatial prediction.
problem Predicting multivariate measurements at unobserved locations with spatial dependencies.
method Spatial blind source separation as a pre-processing tool compared to Cokriging and neural networks.
result Spatial blind source separation simplifies spatial prediction by avoiding cross-dependencies.
Calibration of simplified vine copulas using noise contrastive estimation
problem Modeling complex multivariate dependence structures
method Noise contrastive estimation for calibration
result Improved model accuracy when simplifying assumption is violated
Residual Network (ResNet) is the state-of-the-art architecture that realizes successful training of really deep neural network. It is also known that good weight initialization of neural network avoids problem of vanishing/exploding gradients. In this paper, simplified models of ResNets are analyzed. We argue that good…
Simplified Bayesian neural networks reduce model complexity and improve interpretability.
problem Over-parameterization and interpretability issues in deep learning models.
method Input-skip Latent Binary Bayesian Neural Networks (LBBNNs) that allow covariates to skip layers or be excluded.
result Significant reduction in model complexity (over 99%) with minimal loss in accuracy and uncertainty.
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…
A simplified trisection is a trisection map on a 4-manifold such that, in its critical value set, there is no double point and cusps only appear in triples on innermost fold circles. We give a necessary and sufficient condition for a 3-tuple of systems of simple closed curves in a surface to be a diagram of a simplifie…
Simplified proof for Cheeger's isoperimetric constant.
problem Cheeger's isoperimetric constant
method Simplified proof of Buser's result
result Simplified proof for Cheeger's isoperimetric constant
Classifies 3-manifolds from simplified (2,0)-trisections of 4-manifolds.
problem Classifying 3-manifolds from simplified (2,0)-trisections of 4-manifolds.
method Classifies vertical 3-manifolds as preimages of arcs on the plane for simplified (2,0)-trisection maps.
result Each 6-tuple of vertical 3-manifolds determines the source 4-manifold uniquely up to orientation reversing diffeomorphisms.
With the growth of deep learning, how to describe deep neural networks unifiedly is becoming an important issue. We first formalize neural networks mathematically with their directed graph representations, and prove a generation theorem about the induced networks of connected directed acyclic graphs. Then, we set up a …
Simplified GAN model shows how discriminator improves generalization.
problem Understanding GAN's generalization ability and avoiding memorization.
method Analyzing a simplified GAN model with early stopping and Wasserstein metric.
result Generalization error escapes from curse of dimensionality with early stopping.
A new method approximates tangent spaces to simplify neural networks.
problem Efficiency of hierarchical neural networks is hindered by their complexity and training requirements.
method Approximates tangent subspace to enable sparse representation and switch to shallow networks.
result The method improves and sometimes surpasses the performance of original networks after a few epochs.
Large deviation principle for deep neural networks with ReLU activation.
problem Understanding the behavior of deep neural networks with ReLU activation.
method Proving a large deviation principle for networks with Gaussian weights and ReLU activation functions.
result Simplified expressions and power-series expansions for the ReLU case.
PSiLON Net uses weight normalization and 1-path-norm regularization for efficient learning and sparsity.
problem Efficient learning and sparsity in neural networks with limited data.
method PSiLON Net employs weight normalization and 1-path-norm regularization to simplify the 1-path-norm and achieve efficient learning and near-sparse parameters.
result PSiLON Net achieves reliable optimization and strong performance in the small data regime.
Shapes of four dimensional spaces can be studied effectively via maps to standard surfaces. We explain, and illustrate by quintessential examples, how to simplify such generic maps on 4-manifolds topologically, in order to derive simple decompositions into much better understood manifold pieces. Our methods not only al…
mlr3torch simplifies deep learning in R for tabular and image data.
problem Simplifying deep learning workflows in R for various data types.
method Built on torch, integrates mlr3 ecosystem, supports custom architectures.
result Extensible framework for tabular and image data, including preprocessing and model definition.
Researchers shrink U-Net to find limits of retinal vessel segmentation.
problem Improving retinal vessel segmentation with deep learning.
method Modified U-Net with functional blocks, then simplified to extreme conditions.
result U-Net does not degrade until very minimal configurations.
Deep learning models have been the subject of study from various perspectives, for example, their training process, interpretation, generalization error, robustness to adversarial attacks, etc. A trained model is defined by its decision boundaries, and therefore, many of the studies about deep learning models speculate…
Simplified proof of Honda-Huang's contact convexity result.
problem Contact convexity in high dimensions
method Simplified proof of Honda-Huang's main result
result Main result from Honda-Huang's paper simplified and presented
The EMNLP 2018 workshop BlackboxNLP was dedicated to resources and techniques specifically developed for analyzing and understanding the inner-workings and representations acquired by neural models of language. Approaches included: systematic manipulation of input to neural networks and investigating the impact on thei…