Proposes a new framework for resource-limited recommendation.
problem Resource constraints affect user choices in recommendation tasks.
method Interest-behavior multiplicative network with MRRNNs and resource-limited branch.
result Framework effectively predicts user interactions considering resource limitations.
A new algorithm for resource-aware multi-armed bandits minimizes regret.
problem Optimizing resource usage in a multi-armed bandit problem with censored observations.
method UCB-inspired online learning algorithm with theoretical regret analysis.
result The proposed algorithm outperforms standard multi-armed bandit algorithms in simulations.
Caratheodory's axiom limits arbitrage in resource-limited systems.
problem Non-arbitrage constraints in resource-limited financial systems.
method Preserving Caratheodory's axiom in resource-limited systems.
result Exponential family is the necessary geometric structure for both thermodynamics and finance.
Survey of knowledge distillation for resource-limited devices.
problem Deploying large deep learning models on resource-limited devices.
method Knowledge distillation using a smaller model trained with information from a larger model.
result A new metric (distillation metric) for comparing different knowledge distillation algorithms.
CompactNet optimizes CNN models for resource-limited platforms.
problem Challenges in implementing CNN models on resource-limited platforms.
method Guided by a simulator, CompactNet progressively trims a pre-trained network to achieve target speedup while maintaining accuracy.
result Achieves up to 1.8x kernel computation speedup on embedded platforms.
A new RNN architecture reduces model size and improves performance.
problem Overparameterization and resource limitations in RNNs.
method Jointly encodes weight matrices using tensor-train factorization.
result Reduces model size by several orders of magnitude without sacrificing performance.
Improved PAC guarantees for multi-agent reinforcement learning with noisy communication.
problem Improving exploration in cooperative multi-agent reinforcement learning with communication constraints.
method Develops PAC guarantees for multiple concurrent MDPs with noisy and resource-limited communication.
result Theoretical and empirical improvements in sample complexity for information fusion.
OpTorch optimizes deep learning for resource-limited environments.
problem Resource constraints in deep learning training.
method Optimized deep learning pipelines in training time and memory.
result Achieved similar accuracy to existing libraries with reduced memory usage.
Paper proposes a new binary quantization method for faster DNN inference.
problem Accelerating deep neural network inference on resource-limited devices.
method Quantized Compressed Sensing (QCS) for binary quantization.
result The proposed method preserves benefits of standard methods while reducing quantization error.
Unified framework for accelerating DNNs on resource-limited platforms.
problem Accelerating DNN execution on resource-limited platforms.
method Block-based pruning framework with reweighted regularization.
result First universal framework for both CNNs and RNNs with real-time acceleration and no accuracy compromise.
The paper examines efficient algorithms for linear regression over resource-limited networks.
problem Efficient communication in distributed learning over resource-limited networks.
method Developed algorithms for communication-efficient learning of linear regression tasks.
result The algorithms enable a tradeoff between communication and learning with theoretical performance guarantees.
Method finds optimal binary classification rules under weighted misclassification loss.
problem Optimal binary classification rules for resource-limited settings with cost-sensitive decisions.
method Ensemble learning to derive prediction scores and associated thresholds minimizing weighted misclassification loss.
result Jointly derived score and threshold outperforms methods that derive score first and threshold second.
Mirror Descent framework for efficient neural network quantization.
problem Efficiently quantize large neural networks for resource-limited devices.
method Introduce Mirror Descent framework for constrained optimization of quantized neural networks.
result Mirror Descent framework achieves state-of-the-art performance in quantized neural networks.
Modeling alignment as resource-limited cognitive processes, researchers derive performance bounds.
problem Systematic deviations in feedback-based alignment of large language models.
method Modeling alignment as a two-stage cascade UoHoY given S, with cognitive and total capacities. result Capacity-coupled Alignment Performance Interval derived from Fano and PAC-Bayes bounds.
This paper investigates compression techniques for deep neural networks to reduce their size without sacrificing performance.
problem Compression of large deep neural networks for resource-limited platforms.
method Weight pruning, quantization, and lossless weight matrix representations based on source coding.
result Achieved up to 165 times compression rate while maintaining or improving model performance.
A new method prunes neural networks faster and more efficiently.
problem Reducing training time and memory usage for neural networks.
method Set-based Task-Adaptive Meta Pruning (STAMP) that meta-learns a pruning mask.
result Significantly improved compression rates and faster training speed.
Framework predicts household incomes using common indicators across regions.
problem Finding a single policy for multiple regions with diverse issues.
method Regression analysis and Minimum Description Length (MDL) principle.
result Framework identifies largest regions with common indicators for efficient income prediction.
Randomly shuffled kernels can be compressed efficiently.
problem Reducing storage cost of CNN parameters on resource-limited platforms.
method Randomly-shuffled tensor decomposition (RsTD) to embed kernels into random low-rank subspaces.
result CNNs can be significantly compressed even with randomly shuffled kernels, achieving more stable accuracy.
We study probability measures induced by set functions with constraints. Such measures arise in a variety of real-world settings, where prior knowledge, resource limitations, or other pragmatic considerations impose constraints. We consider the task of rapidly sampling from such constrained measures, and develop fast M…
Self distillation boosts CNN accuracy without increasing model size.
problem Improving CNN accuracy in resource-limited domains.
method Divide and compress knowledge within the network structure.
result Average accuracy improvement of 2.65% across various networks.
The aim of this work is to address the question of whether we can in principle design rational decision-making agents or artificial intelligences embedded in computable physics such that their decisions are optimal in reasonable mathematical senses. Recent developments in rare event probability estimation, recursive ba…
EnSyth enhances deep learning models' predictability through ensemble synthesis.
problem Compressing deep learning models for resource-limited environments while maintaining accuracy.
method EnSyth generates diverse compressed models, synthesizes their outputs, and eliminates the least performing combinations.
result EnSyth outperforms baseline models on CIFAR-10 and CIFAR-5 datasets with LeNet-5.
Subjective expected utility theory assumes that decision-makers possess unlimited computational resources to reason about their choices; however, virtually all decisions in everyday life are made under resource constraints - i.e. decision-makers are bounded in their rationality. Here we experimentally tested the predic…
Pruning filters in neural networks improves performance and reduces costs.
problem Large neural networks have high inference costs and limited resource usage.
method Batch Bridgeout for efficient pruning of convolutional filters.
result Batch Bridgeout trained networks achieve higher accuracy across various pruning intensities.
A system for Operational Risk management based on the computational paradigm of Bayesian Networks is presented. The algorithm allows the construction of a Bayesian Network targeted for each bank using only internal loss data, and takes into account in a simple and realistic way the correlations among different processe…
Paper proposes efficient multivariate spatial Fay-Herriot models using variational autoencoders.
problem Estimating population characteristics in small areas with limited data.
method Integrates multivariate spatial Fay-Herriot model with variational autoencoders to leverage spatial structure efficiently.
result Significant computational efficiency improvements for high-dimensional datasets.
New algorithms improve GP inference without approximations, achieving better results.
problem Inexact stochastic optimization methods in Gaussian Processes leading to biased results.
method Exact stochastic inference for GPs with finite dimensional RKHS, extending to infinite dimensions.
result Achieves better experimental results than existing methods in constrained resource settings.
Study selective classification with limited feedback in online learning.
problem Resource-limited and safety-critical domains where feedback is only received on abstentions.
method Versioning-based schemes for minimizing mistakes and abstentions.
result Constructed schemes that make few mistakes and minimal excess abstentions.
This paper defines resource-constrained classifier performance and its impact on algorithm choice.
problem Classification tasks in resource-constrained settings where actions are limited.
method Defines resource-constrained classifier performance and discusses gains and lift.
result Gains and lift metrics can lead to different algorithm choices.
Bounded rationality, that is, decision-making and planning under resource limitations, is widely regarded as an important open problem in artificial intelligence, reinforcement learning, computational neuroscience and economics. This paper offers a consolidated presentation of a theory of bounded rationality based on i…
Unified framework for constrained online decision-making.
problem Sequential decisions under stage-wise feasibility constraints.
method Upper counterfactual confidence bounds and generalized eluder dimension.
result Principled foundation for constrained sequential decision-making.
A principle for specialized decision-making divides complex problems into manageable parts.
problem Complex decision-making problems beyond individual capabilities.
method An on-line learning rule that learns a partitioning of the problem space for specialized linear policies.
result The approach solves problems that exceed individual decision-makers' capabilities.
Efficiently preserves old class knowledge in memory-limited settings.
problem Catastrophic forgetting in class-incremental learning.
method Memory-efficient exemplar preserving scheme and domain-compatible feature extractors.
result Low-fidelity exemplar samples can replace high-fidelity ones with less memory cost.
Survey of knowledge distillation for model compression.
problem Deploying large deep models on resource-limited devices.
method Knowledge distillation from large teacher models to small student models.
result Effective model compression and acceleration.
t-distributed Stochastic Neighborhood Embedding (t-SNE) is a method for dimensionality reduction and visualization that has become widely popular in recent years. Efficient implementations of t-SNE are available, but they scale poorly to datasets with hundreds of thousands to millions of high dimensional data-points. W…
The paper provides theoretical guarantees for hashing-based neural net compression.
problem Rigorous theoretical guarantees on neural net compression methods.
method Random linear sketching and HashedNets architecture.
result Provable guarantees on the performance of hashing-based neural net compression.
This paper analyzes and improves convergence in federated learning with biased client selection.
problem Analyzing convergence in federated learning with biased client selection.
method First convergence analysis of federated optimization for biased client selection strategies, proposing Power-of-Choice framework.
result Power-of-Choice strategies converge up to 3 times faster and give 10% higher test accuracy than random selection.
Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited applications. With the aim of improving sample efficiency and learning performa…
SCAN divides deep neural networks into shallow classifiers for efficient deployment.
problem Explosive growth in storage and computation limits deep neural networks on edge devices.
method SCAN divides networks into shallow classifiers, uses attention modules and knowledge distillation, and employs a threshold-controlled scalable inference mechanism.
result SCAN achieves significant performance gain on CIFAR100 and ImageNet without hyper-parameter adjustments.
Project condenses neural nets to make ML accessible in healthcare, reducing computational burden.
problem Limited computational resources in healthcare settings, particularly in third-world nations.
method Pruning unused neurons, modifying RNN structure, and quantizing weights to reduce neural net size and complexity.
result Increased computational efficiency without compromising accuracy, some methods even improving accuracy.
Theoretical framework for neural network compression using sparsity norms.
problem Understanding and quantifying compressibility and accuracy trade-offs in neural networks.
method Using sparsity-sensitive ℓ_q-norm to characterize compressibility and developing adaptive pruning algorithms.
result Theoretical relationship between network sparsity and compressibility with controlled accuracy degradation.
A novel method for efficient CDRL over wireless networks.
problem Challenges in collaborative deep reinforcement learning over wireless networks.
method Semantic-aware heterogeneous federated deep reinforcement learning (HFDRL) algorithm.
result Superior performance compared to state-of-the-art baselines.
Growth of monetary assets and debts is commonly described by the formula of compound interest which for the case of continuous compounding is the exponential growth law. Its differential form is dc/dt = i c where dc/dt describes the rate of monetary growth, i the compounded interest rate and c the actual principal. Exp…
New method optimizes weights and quantizers in ternary neural networks.
problem Reducing model size and computational cost in deep neural networks.
method Simultaneous optimization of weights and quantizers using truncated Gaussian approximation.
result 3.9-2.16% accuracy loss in ImageNet classification tasks.
A method to reduce knowledge graph embedding models by binarizing parameters.
problem Large memory requirements for tensor factorization models in knowledge graph completion.
method Introducing a quantization function to binarize parameters of CP tensor decomposition.
result Successfully reduced model size by more than an order of magnitude while maintaining task performance.
Compact neural network for ECG classification reduces resource needs.
problem Current reliance on deep learning for ECG analysis requires extensive resources and large datasets.
method Simple ANN architecture with advanced feature engineering.
result Achieved 97.36% accuracy in classifying 4 types of arrhythmias.
Improved animated faces using audiovisual and modality dropout.
problem Creating realistic animated faces using speech and visual cues.
method Training a deep learning model with modality dropout to balance audio and visual inputs.
result Modality dropout improves viewer preference for audiovisual-driven animation.
Finite resources limit false discovery rate control in structured hypothesis spaces.
problem Controlling false discovery rate in hypothesis testing with finite data and structured hypothesis spaces.
method Framework for exact FDR control and adaptive power maximization.
result Exact FDR control and adaptive power maximization.