A new framework generates large hierarchical search spaces for neural architectures.
problem Discovering neural architectures from simple blocks is hard.
method Context-free grammars for a unified, scalable search space.
result Efficiently searches over complete architectures, outperforming existing methods.
Novel graph network learns hierarchical network structure.
problem Lack of information in hierarchical network topology.
method Hierarchical clustering for multiscale decomposition, graph convolutional layers.
result Competitive performance on citation network benchmark.
Transformer models perform slower than convolutional networks in learning hierarchical language structures.
problem Understanding how neural networks learn hierarchical language structures.
method Theoretical scaling laws and empirical validation of neural network performance.
result Convolutional networks outperform transformers in learning hierarchical language structures.
U-Nets use belief propagation for efficient image denoising and classification.
problem Efficiently denoise and classify images using generative hierarchical models.
method Interpreted U-Nets as implementing belief propagation in tree-structured models.
result U-Nets can efficiently approximate denoising functions with sample complexity bounds.
The Transformer architecture has become increasingly popular over the past two years, owing to its impressive performance on a number of natural language processing (NLP) tasks. However, all Transformer computations occur at the level of word representations and therefore, it may be argued that Transformer models do no…
New MIF architecture improves posterior approximations in Bayesian models.
problem Challenges in variational inference for complex hierarchical models.
method Combines VIP and autoregressive flow with prior information and hierarchical ordering.
result Empirically, MIF delivers tighter posterior approximations and state-of-the-art performance.
Unified framework for modeling hierarchical spaces in design problems.
problem Challenges in modeling hierarchical, conditional, heterogeneous, or tree-structured domains.
method Unified framework combining feature modeling and graph theory, introducing meta and partially-decreed variables.
result Demonstrated effectiveness on complex system design problems, including neural networks and green-aircraft.
Free Random Projection enhances reinforcement learning by naturally incorporating hierarchical structure.
problem Improving reinforcement learning algorithms for better generalization and adaptability.
method Introduces Free Random Projection, a method that uses free probability theory to create random orthogonal matrices encoding hierarchical structure.
result Empirically shows consistent improvement in generalization over standard methods on multi-environment benchmarks.
We propose that the Continual Learning desiderata can be achieved through a neuro-inspired architecture, grounded on Mountcastle's cortical column hypothesis. The proposed architecture involves a single module, called Self-Taught Associative Memory (STAM), which models the function of a cortical column. STAMs are repea…
We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance. Our approach combines a novel hierarchical genetic representation scheme that imitates the modularized design pattern commonly adopted by human ex…
The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS, that generalizes existing weight sharing based NAS approaches. Existing weight shar…
Paper tackles NAS problem by modeling it as a sparse supernet.
problem Neural Architecture Search (NAS) problem, particularly Mixed-Path Search.
method Model NAS as a sparse supernet with sparsity constraints. Use hierarchical accelerated proximal gradient algorithm for optimization.
result Proposed method finds compact, general, and powerful neural architectures.
We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitable framework for encouraging explorations in such hierarchical networks. A natural utilization of this framework is an adversarial setting, w…
The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of Transformer has been attributed to propagating signals over shorter distances, between positions in …
A novel framework combines LLMs and RL for financial portfolio optimization.
problem Optimizing financial portfolios using sentiment analysis and market indicators.
method Hierarchical RL structure with base, meta, and super-agents.
result Achieved a 26% annualized return and Sharpe ratio of 1.2.
A transformer model improves spell correction with hierarchical attention.
problem Improving spell correction accuracy and speed.
method Multi encoder-single decoder transformer architecture with hierarchical attention.
result Significant improvement in CER, WER, and SER error rates.
Deep neural networks have been shown to be very successful at learning feature hierarchies in supervised learning tasks. Generative models, on the other hand, have benefited less from hierarchical models with multiple layers of latent variables. In this paper, we prove that hierarchical latent variable models do not ta…
MTL-NAS combines NAS with GP-MTL for task-agnostic multi-task learning.
problem Designing architectures for diverse tasks with varying priors.
method Disentangled GP-MTL networks, hierarchical feature sharing, and gradient-based search.
result General-purpose model trained once can adapt to multiple tasks.
Architectures for sparse hierarchical representation learning have recently been proposed for graph-structured data, but so far assume the absence of edge features in the graph. We close this gap and propose a method to pool graphs with edge features, inspired by the hierarchical nature of chemistry. In particular, we …
One of the primary challenges of visual storytelling is developing techniques that can maintain the context of the story over long event sequences to generate human-like stories. In this paper, we propose a hierarchical deep learning architecture based on encoder-decoder networks to address this problem. To better help…
New origami structures adapt to over 100 shapes with minimal actuation.
problem Limited shape-morphing capabilities in metamaterials and robotics.
method Hierarchical origami based on polyhedrons, using simple actuation.
result Single structure adapts to over 103 configurations with few actuations.
Model compresses event-like contexts using gated surprise signals.
problem Perceiving a dynamic world as organized events.
method Hierarchical, surprise-gated recurrent neural network architecture.
result Achieves best performance on multiple event processing tasks.
Insights in power grid pixel maps (PGPMs) refer to important facility operating states and unexpected changes in the power grid. Identifying insights helps analysts understand the collaboration of various parts of the grid so that preventive and correct operations can be taken to avoid potential accidents. Existing sol…
DDCL-INCRT learns its own structure during training, reducing unnecessary complexity.
problem Fixed-size neural network architectures require manual tuning, leading to overfitting.
method Combines DDCL (Deep Dual Competitive Learning) and INCRT (Incremental Transformer) to self-organize network structure.
result The network self-organizes into a hierarchy of heads, reducing unnecessary complexity.
The paper reformulates U-Nets as wavelet-based models and applies this to hierarchical VAEs.
problem Theoretical understanding and regularization properties of U-Nets and their relationship to wavelets.
method Formulating a multi-resolution framework to identify U-Nets as finite-dimensional truncations of infinite-dimensional models, proving average pooling corresponds to projection, and identifying HVAEs as discretizations of multi-resolution diffusion processes.
result HVAEs learn a time representation allowing for improved parameter efficiency through weight-sharing.
The staircase property aids deep learning by guiding hierarchical feature learning.
problem Understanding how hierarchical structure influences deep learning performance.
method Defined and proved the staircase property for Boolean hypercube functions, and showed its learnability by layerwise stochastic coordinate descent.
result Staircase functions can be learned in polynomial time using layerwise stochastic coordinate descent on regular neural networks.
It has long been conjectured that hypotheses spaces suitable for data that is compositional in nature, such as text or images, may be more efficiently represented with deep hierarchical networks than with shallow ones. Despite the vast empirical evidence supporting this belief, theoretical justifications to date are li…
Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …
New VAE models reveal hierarchical visual cortex computations.
problem Capturing hierarchical visual cortex computations in generative models.
method Sparse coding hierarchical VAEs trained on natural images with varied generative and recognition components.
result Representations similar to those in visual cortex emerge under inductive biases.
Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended …
In this article we review computational aspects of Deep Learning (DL). Deep learning uses network architectures consisting of hierarchical layers of latent variables to construct predictors for high-dimensional input-output models. Training a deep learning architecture is computationally intensive, and efficient linear…
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.
method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.
result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.
Fractal Flow enhances normalizing flows with interpretable latent space and hierarchical modeling.
problem High-dimensional density estimation and generative modeling challenges.
method Integrates topic modeling (LDA) and fractal strategy into normalizing flows.
result Achieves latent clustering, controllable generation, and superior estimation accuracy.
Convolutional networks outperform shallow classifiers on certain tasks due to hierarchical structure.
problem Understanding why convolutional networks outperform shallow classifiers on specific tasks.
method Approximation theory, visual tasks with deterministic scrambling, and network performance evaluation.
result Hierarchical structure is crucial for convolutional networks' performance on certain tasks, but not all.
DHRL learns interpretable features from visual data.
problem Limited use of deep learning in basic research for interpretable features.
method Generative model chaining, ladder network architecture, latent space regularization.
result DHRL generates disentangled hierarchical features from small datasets.
MolHF generates complex molecules with hierarchical flow-based model.
problem Designing novel molecular structures with desired properties.
method MolHF is a hierarchical normalizing flow model that generates molecular graphs in a coarse-to-fine manner.
result MolHF achieves state-of-the-art performance in random generation and property optimization.
The paper uses deep learning to detect financial market regimes from correlation matrices.
problem Detecting financial market regimes from correlation dynamics.
method Representation learning on block hierarchical SPD correlation matrices using SPDNet, SPD-NetBN, and U-SPDNet models.
result Deep learning models overfit in financial market data, misleading performance metrics.
Recently, the efficiency of automatic neural architecture design has been significantly improved by gradient-based search methods such as DARTS. However, recent literature has brought doubt to the generalization ability of DARTS, arguing that DARTS performs poorly when the search space is changed, i.e, when different s…
New simulation model predicts financial market dynamics with high accuracy.
problem Extreme difficulty in financial market projections due to human behavioural complexity.
method Agent-based modeling with a hierarchical knowledge architecture to simulate diverse human groups.
result Simulator achieves 13.29% deviation in crisis scenarios and lower mean square error under normal conditions.
Proposes EM-HRNN model for better hierarchical language representation.
problem Learning hierarchical representations in natural language processing.
method Introduces latent indicator layer and EM algorithm for training.
result EM-HRNN model outperforms other RNN-based models in document classification.
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
BL learns interpretable optimization structures from data.
problem Learning interpretable optimization structures from data.
method BL parameterizes a compositional utility function from intrinsically interpretable modular blocks.
result BL supports architectures from single to hierarchical compositions, modeling hierarchical optimization structures.
Gated attention improves performance by using a hierarchical mixture of experts.
problem Improving performance of self-attention mechanisms in Transformers.
method Rigorously show that gated attention can be modeled as a hierarchical mixture of experts, providing a theoretical justification for its benefits.
result Gated attention is more sample-efficient than multi-head self-attention, requiring fewer data points to achieve the same estimation error.
Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the bottom-up inference process, the goal of preserving all factors of variations for top-down generation is compromised. Motivated by the conc…
Many recent invertible neural architectures are based on coupling block designs where variables are divided in two subsets which serve as inputs of an easily invertible (usually affine) triangular transformation. While such a transformation is invertible, its Jacobian is very sparse and thus may lack expressiveness. Th…
The counting grid is a grid of microtopics, sparse word/feature distributions. The generative model associated with the grid does not use these microtopics individually. Rather, it groups them in overlapping rectangular windows and uses these grouped microtopics as either mixture or admixture components. This paper bui…
A theoretical framework for deep learning is proposed to explain its effectiveness.
problem Lack of a comprehensive theory explaining deep learning's effectiveness.
method Integrates three characteristics into a graphical model called neurashed.
result Explains common empirical patterns in deep learning and provides insights into regularization and elasticity.
Enhances neural forecasting for hierarchically organized time series data.
problem Probabilistic coherent forecasting of time series data across different levels of aggregation.
method Proposes a coherent multivariate mixture output for neural forecasting architectures, optimizing with a composite likelihood objective.
result 13.2% average accuracy improvements on most datasets compared to state-of-the-art baselines.