Research
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

113226338451 · Jun 202019922001200920172026
48 results for differentiable architecture

Differentially-private FNAS protects privacy while collaboratively searching for neural architectures.

problem Collaborative neural architecture search with privacy concerns.
method Federated Neural Architecture Search (FNAS) with differential privacy (DP-FNAS).
result DP-FNAS can search for highly-performant neural architectures while protecting individual parties' privacy.

This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable search space, our method is based on the continuous relaxation of the architectu…

2018-06-24abs ↗pdf ↗

Proposes a method to improve neural architectures reproducibly.

problem Lack of reproducibility in Neural Architecture Transformer (NAT).
method Differentiable Neural Architecture Transformation (DNAT).
result DNAT outperforms NAT and is applicable to various models and datasets.

Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaining a search cost orders of magnitude lower than reinforcement learning (RL) based NAS. However, DNAS…

2019-12-16abs ↗pdf ↗

New model predicts neural network performance from early training epochs, incorporating architecture impact.

problem Predicting neural network performance from early training epochs, neglecting architecture impact.
method Architecture-aware graph ordinary differential equation model.
result Model outperforms state-of-the-art methods for MLP and CNN learning curves.

Gradients of neural networks can be computed efficiently for any architecture, but some applications require differential operators with higher time complexity. We describe a family of restricted neural network architectures that allow efficient computation of a family of differential operators involving dimension-wise…

2019-12-08abs ↗pdf ↗

DNArch learns CNN architectures by backpropagation.

problem Discovering optimal CNN architectures.
method Differentiable Neural Architectures (DNArch) learns CNN architectures by backpropagation, controlling kernel sizes, channels, downsampling positions, and depth.
result DNArch finds performant CNN architectures across various tasks.

Differentiable NAS frameworks grow networks wider and deeper, revealing biases in wiring evolution.

problem Understanding the evolution of neural architecture wiring in differentiable NAS methods.
method Unified view on searching algorithms, local cost minimization, empirical and theoretical analyses.
result Implicit inductive biases cause observed searching patterns in differentiable NAS methods.

FiGS searches over a larger space of architectures for efficient mobile models.

problem Designing small, efficient deep networks for mobile devices.
method Differentiable search method using sparse regularization and Logistic-Sigmoid distribution.
result FiGS produces state-of-the-art parameter-efficient models on ImageNet and improves object detection performance.

DANCE optimizes neural network and accelerator design for faster, more efficient DNN execution.

problem Challenges in optimizing neural network and accelerator design for efficient DNN execution.
method Differentiable approach to co-exploration of accelerator and network architecture design.
result Significantly shorter time to achieve superior accuracy and hardware cost metrics.

HardCoRe-NAS finds fitting neural networks adhering to hard resource constraints.

problem Finding fitting neural networks that adhere to hard resource constraints.
method Accurate formulation of resource requirement and scalable search method.
result HardCoRe-NAS generates state-of-the-art architectures strictly satisfying hard resource constraints.

For network architecture search (NAS), it is crucial but challenging to simultaneously guarantee both effectiveness and efficiency. Towards achieving this goal, we develop a differentiable NAS solution, where the search space includes arbitrary feed-forward network consisting of the predefined number of connections. Be…

2019-05-06abs ↗pdf ↗

New method recovers transportable DAG structures from different datasets.

problem Inference of DAG structures is computationally expensive and lacks transportability.
method Introduces D-Struct, a differentiable architecture that recovers transportable DAG structures.
result D-Struct recovers transportable DAG structures from different datasets.

We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back-propagation, while maintaining the completeness and differentiability of the NAS pipeline.…

2018-12-24abs ↗pdf ↗

PDNAS optimizes GNN architectures for diverse datasets.

problem Inadequate adaptability and combinatorial search space in GNNs.
method Dual architecture search (micro- and macro-architectures) with gradient-based optimization.
result PDNAS finds deeper GNNs with better performance on diverse datasets.

Bonsai-Net efficiently discovers state-of-the-art models with fewer parameters.

problem Efficiently discovering state-of-the-art neural architectures with minimal computational expense.
method Bonsai-Net uses a modified differential pruner to explore a relaxed search space.
result Bonsai-Net consistently discovers better architectures than random search with fewer parameters.

Paper presents an ADMM-based approach to efficiently integrate quadratic programming layers into neural networks.

problem Integrating quadratic programs into neural networks for optimization.
method An ADMM-based network layer architecture for solving quadratic programs efficiently.
result The ADMM layer is approximately an order of magnitude faster than existing methods for medium scaled problems.

Theory explains why DARTS favors deep architectures over shallow ones.

problem DARTS selects architectures with dominated skip connections, leading to performance degradation.
method Theoretical analysis of operations' effects on network optimization; introduces sparse binary gates and path-depth-wise regularization.
result Theoretical proof that architectures with more skip connections converge faster.

New neural stack and Turing Machine architectures prove stability and computational power.

problem Designing stable neural network architectures for Turing Machine simulation.
method Introducing neural stack and Turing Machine architectures, proving stability and computational equivalence.
result Differentiable nnTM with bounded neurons can simulate Turing Machine in real-time and is equivalent to UTM.

Neural architecture search (NAS) recently attracts much research attention because of its ability to identify better architectures than handcrafted ones. However, many NAS methods, which optimize the search process in a discrete search space, need many GPU days for convergence. Recently, DARTS, which constructs a diffe…

2019-05-30abs ↗pdf ↗

DrNAS improves neural architecture search with Dirichlet distribution and progressive learning.

problem Efficiently search for neural architectures with improved generalization and exploration.
method Formulates architecture search as a distribution learning problem using Dirichlet distribution and gradient-based optimization. Introduces a progressive learning scheme to handle large-scale tasks.
result Achieves state-of-the-art results on CIFAR-10 and ImageNet, demonstrating improved generalization and exploration.

Proposes a new method to optimize graph neural network architectures on heterogeneous information networks.

problem Weaknesses in instability and inflexibility of existing graph neural architecture search methods.
method Partial Message Meta Multigraph search (PMMM) using a differentiable framework to search for a meaningful meta multigraph.
result Significantly more stable and effective than state-of-the-art heterogeneous GNNs.

In many learning situations, resources at inference time are significantly more constrained than resources at training time. This paper studies a general paradigm, called Differentiable ARchitecture Compression (DARC), that combines model compression and architecture search to learn models that are resource-efficient a…

2019-05-20abs ↗pdf ↗

New methods speed up training of differentially private deep learning models.

problem Training differentially private deep learning models is slower than non-private models.
method Derive and implement new per-example gradient clipping methods compatible with auto-differentiation.
result Significant training speed-ups (54x - 94x) for various models and architectures.

This work proposes searching for optimal operation distribution in neural architecture search.

problem Finding optimal neural architecture with specific operations and connections.
method Search for the optimal operation distribution, providing a stochastic and approximate solution.
result Operation distribution holds enough discriminating power to reliably identify a solution and is easier to optimise than traditional encodings.

Differentiable Architecture Search (DARTS) has attracted a lot of attention due to its simplicity and small search costs achieved by a continuous relaxation and an approximation of the resulting bi-level optimization problem. However, DARTS does not work robustly for new problems: we identify a wide range of search spa…

2019-09-20abs ↗pdf ↗

This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks. These layers encode constraints and complex dependencies between the hidden states that traditional convoluti…

2017-03-01abs ↗pdf ↗

Pruning is one of the most effective model reduction techniques. Deep networks require massive computation and such models need to be compressed to bring them on edge devices. Most existing pruning techniques are focused on vision-based models like convolutional networks, while text-based models are still evolving. The…

2019-09-10abs ↗pdf ↗

CRUs model irregular time series with continuous hidden states.

problem Handling irregular time intervals in sequential data.
method Continuous Recurrent Units (CRUs) that integrate hidden states via a linear stochastic differential equation.
result CRUs outperform methods based on neural ordinary differential equations in irregular time series interpolation.

NDM incorporates geometric structure into neural networks for better optimization and interpretability.

problem Efficient and interpretable deep learning architectures.
method NDM is a neural network architecture that explicitly incorporates geometric structure into its design, using a Coordinate Layer, Geometric Layer, and Evolution Layer.
result NDM provides intrinsic regularization, enhancing generalization and robustness.

We provide a proof of backpropagation algorithm in matrix notation.

problem The lack of a full induction proof of backpropagation algorithm in matrix notation.
method We provide a full induction proof of the BP algorithm in matrix notation, situating it in the framework of matrix differential calculus.
result We prove the validity of the backpropagation algorithm in inductive form.

Novel NAS method balances performance and hardware metrics efficiently.

problem Challenging multi-objective optimization in neural architecture search.
method Parameterizes joint architectural distribution via hypernetwork conditioned on hardware features and preferences.
result Zero-shot transferability to new devices with representative and diverse architectures.

To understand the fundamental trade-offs between training stability, temporal dynamics and architectural complexity of recurrent neural networks~(RNNs), we directly analyze RNN architectures using numerical methods of ordinary differential equations~(ODEs). We define a general family of RNNs--the ODERNNs--by relating t…

2019-04-29abs ↗pdf ↗

SLAM-net learns to navigate visually in challenging indoor environments.

problem Challenges in SLAM for visual robot navigation, especially in noisy conditions.
method Differentiable SLAM Network (SLAM-net) that encodes a particle filter SLAM algorithm in a differentiable graph and learns components through backpropagation.
result Significantly outperforms ORB-SLAM in noisy conditions and improves the Habitat Challenge 2020 PointNav task.

FNO-DEQ solves steady-state PDEs as fixed points, outperforming traditional FNOs.

problem Lack of understanding in designing neural network architectures for PDEs.
method Proposes FNO-DEQ, a deep equilibrium architecture that solves steady-state PDEs as fixed points.
result FNO-DEQ outperforms FNO-based architectures in predicting solutions to steady-state PDEs.