Paper benchmarks causal discovery techniques based on accuracy of inference.
problem Comparing causal discovery algorithms for accuracy of inference tasks.
method Categorized algorithms into two categories and compared them on three perspectives: structural accuracy, standard predictive accuracy, and counterfactual inference.
result Structural accuracy does not correlate with inferencing accuracy, and algorithms perform poorly with many variables.
Structured linear substitutions improve both efficiency and accuracy in neural networks.
problem Improving neural network efficiency and accuracy tradeoff.
method Replacing linear components in pointwise convolutions with structured linear decompositions.
result Structured layers provide Pareto-optimal benefits in efficiency/accuracy.
Hierarchical Block Sparse Neural Networks improve both accuracy and runtime efficiency of sparse DNNs.
problem Inefficiency of sparse DNNs on regular parallel hardware due to irregular computation.
method Introducing HBsNN, a structured sparse neural network that balances accuracy and runtime efficiency.
result HBsNN achieves better runtime performance and accuracy than unstructured and highly structured sparse models.
CNNs adapted for graphs match image CNNs without prior knowledge.
problem Matching CNN performance on graph-structured data without prior knowledge.
method Strided convolutions and data augmentation on graphs.
result Significant accuracy improvement on fMRI data.
Paper explores tradeoff between standard and robust accuracy for latent models.
problem Tradeoff between standard accuracy and robust accuracy in adversarial training.
method Revisits adversarial training for latent models, considering Gaussian mixture and generalized linear models.
result Low-dimensional manifold structure mitigates the tradeoff between standard and robust accuracy.
PS8-Net improves eight-state protein secondary structure prediction accuracy.
problem Precise prediction of eight-state protein secondary structure (PSS) is crucial in bioinformatics.
method PS8-Net is a new deep convolutional neural network (DCNN) that uses a PS8 module with skip connections to enhance accuracy.
result PS8-Net achieves 76.89% Q8 accuracy on benchmark datasets.
Sparsity helps reduce the computational complexity of deep neural networks by skipping zeros. Taking advantage of sparsity is listed as a high priority in next generation DNN accelerators such as TPU. The structure of sparsity, i.e., the granularity of pruning, affects the efficiency of hardware accelerator design as w…
We derive caplet volatilities for quadratic models, providing an asymptotic approximation.
problem Calculating caplet volatilities for quadratic term-structure models.
method Asymptotic approximation for caplet volatilities under quadratic models.
result Asymptotic accuracy of the derived caplet volatilities.
OTSL improves structure learning accuracy with out-of-sample and resampling strategies.
problem Determining optimal hyperparameters for structure learning algorithms.
method Out-of-sample Tuning for Structure Learning (OTSL) using resampling strategies.
result Improves graphical accuracy of structure learning algorithms.
VB approach for dynamic network models improves efficiency and accuracy.
problem Estimating dynamic network models in large-scale systems.
method Variational Bayesian inference for network autoregression.
result VB approach detects proper active structures and achieves similar or better accuracy.
Paper speeds up structured output prediction without sacrificing accuracy.
problem Computational inefficiency in predicting structured outputs.
method Learning to search approach to train a speedup classifier.
result Speedup classifier outperforms greedy search in terms of speed.
Kaleidoscope matrices improve model quality and inference speed.
problem Choosing structured linear transformations for efficiency and accuracy.
method Introduce kaleidoscope matrices that can capture any structured matrix with near-optimal space and time complexity. Learn these matrices automatically within end-to-end pipelines.
result Kaleidoscope matrices can improve model quality and inference speed.
CNNs improve positioning accuracy in massive MIMO systems.
problem Improving positioning accuracy in massive MIMO systems.
method Applying CNNs to learn sparse massive MIMO channel fingerprints.
result Moderately deep CNNs achieve fractional-wavelength positioning accuracy.
Novel hybrid method for Bayesian network structure learning reduces computational time without sacrificing accuracy.
problem Bayesian network structure learning efficiency and accuracy trade-off.
method Partitioned PC (pPC), p-value adjacency thresholding (PATH), hybrid greedy initialization (HGI). result pHGS achieves significant computational reductions compared to the PC algorithm without sacrificing structure learning accuracy.
The paper explores feature selection for improving classification accuracy in event logs.
problem Improving machine learning-based interactive root cause analysis for business process instances.
method Developed structural features from event logs and compared six feature selection algorithms.
result Feature selection can improve classification accuracy without significantly increasing run-time.
New CFNN architecture approximates functions with machine accuracy.
problem Function approximation with high precision.
method Chebyshev Feature Neural Network (CFNN) with learnable frequencies.
result Achieves machine accuracy in function approximation.
Study improves epidemic forecasting with a sparsified GSRNN.
problem Epidemic forecasting on real-world health data.
method Graph-structured recurrent neural network (GSRNN) with sparsification via transformed-ℓ1 penalty. result Maintained prediction accuracy with 70% of network weights being zero.
Post-estimation smoothing improves prediction accuracy with structural indices.
problem Using natural structural indices in machine learning without losing robustness.
method A post-estimation smoothing operator that separates from the original predictor.
result Post-estimation smoothing improves accuracy over original predictors under simple conditions.
Network Lens identifies node behaviors in heterogeneous networks with high accuracy.
problem Identifying different behaviors in various parts of large heterogeneous networks.
method Zoom into network using different-sized lenses to capture local structure, weight signatures to predict node labels.
result Achieved a peak accuracy of ~42% on two networks with ~100,000 and ~1,000,000 nodes, significantly better than random.
PCONV combines fine-grained and coarse-grained pruning for efficient DNN inference on mobile devices.
problem Achieving high sparsity and accuracy in DNN weight pruning for real-time mobile execution.
method PCONV introduces a new sparsity dimension by combining fine-grained pruning patterns inside coarse-grained structures.
result PCONV outperforms state-of-the-art frameworks in speed and efficiency without accuracy loss.
Generative grading improves automated feedback for structured problems.
problem Difficulty in providing high-quality feedback on structured assignments.
method Generative descriptions of student cognition, probabilistic programs, and learning to infer feedback.
result Achieved near-human accuracy in grading and feedback across diverse domains.
ISAAC audits deep models for drug-target interactions, revealing structural differences.
problem Deep models for DTI often use irrelevant features, making them hard to evaluate.
method ISAAC uses intervention-based structural auditing to evaluate model sensitivity.
result ISAAC reveals significant structural differences in DTI models' reasoning.
Improved protein Q8 secondary structure prediction to 70.7% accuracy.
problem Protein secondary structure prediction accuracy improvement.
method Diverse neural network architectures, ensemble approach, unbiased performance measures.
result 70.7% accuracy on Q8 secondary structure prediction, statistically indistinguishable from top predictors.
Constraint-based algorithms often perform worse in terms of accuracy but not speed compared to score-based algorithms.
problem Comparing the performance of constraint-based, score-based, and hybrid algorithms in learning Bayesian network structures.
method Comparison of algorithms using simulated and real-world data, focusing on accuracy and speed.
result Constraint-based algorithms are often less accurate than score-based algorithms but not significantly faster.
VC-PCR improves prediction by clustering correlated variables.
problem Decreased prediction accuracy due to cluster structure in predictor variables.
method Supervised variable selection and clustering to integrate cluster information into a sparse modeling process.
result VC-PCR achieves better prediction, variable selection, and clustering performance.
New neural network units resist adversarial attacks effectively.
problem Adversarial attacks on neural networks that misclassify inputs.
method Introduced RBFI units with non-linear structure.
result RBFI units maintain high accuracy in adversarial attacks.
Deep neural network improves amino acid side chain prediction accuracy.
problem Predicting amino acid side chain conformation for protein modeling and design.
method Deep neural network architecture without physics-based assumptions.
result Improved accuracy by more than 25% for aromatic residues.
BMRS offers a Bayesian approach to structured pruning of neural networks.
problem Overparameterized neural networks lead to high compute costs.
method Bayesian Model Reduction for Structured pruning (BMRS) based on two recent methods: Bayesian structured pruning with multiplicative noise and Bayesian model reduction.
result BMRS yields high compression rates and accuracy without tuning thresholds.
Improved video tracking accuracy with active learning.
problem Efficiently predicting object matches in videos with active learning.
method Adversarial approach for active learning with structured prediction domains.
result Better accuracy and computational efficiency for object tracking.
Develops a fast, accurate method for comparing networks.
problem Comparing networks with repeated observations and varying sizes/sparsity.
method A novel two-sample hypothesis testing method with theoretical guarantees.
result Outperforms existing tools in speed and accuracy, power-optimal.
GTDL methods fail to accurately model feature interactions in tabular data.
problem Accurate modeling of feature interactions in tabular data.
method Graph-based tabular deep learning methods using attention mechanisms and message-passing schemes.
result Current GTDL methods fail to recover meaningful feature interactions due to poor edge recovery.
Paper learns tree-structured models from distributed data efficiently.
problem Learning tree-structured Gaussian graphical models from distributed data with limited communication.
method Communication-efficient strategies for central node to learn structure from distributed data.
result Tree structure can be reliably recovered even with limited information (signs of local data samples).
The paper analyzes the complexity of sparse label propagation on networks.
problem Computational complexity of sparse label propagation on network data.
method Characterization of iterations for achieving a prescribed accuracy using a first-order oracle model.
result An upper bound on iterations required for accuracy, showing sharpness for chain structures.
Convolutional network predicts DNA chromatin structure from sequence images.
problem Predicting chromatin structure from DNA sequences.
method Developed a convolutional neural network using image-representation of DNA sequences.
result The method outperforms existing methods in prediction accuracy and training time.
Structured prediction is a powerful framework for coping with joint prediction of interacting outputs. A central difficulty in using this framework is that often the correct label dependence structure is unknown. At the same time, we would like to avoid an overly complex structure that will lead to intractable predicti…
This work proposes an attention mechanism for structured sparsity in neural networks.
problem Uncontrolled sparsity in neural networks leads to significant accuracy drops.
method An attention mechanism that controls sparsity intensity and network pruning.
result The proposed method outperforms baseline methods by 6% on CIFAR-10.
In healthcare applications, temporal variables that encode movement, health status and longitudinal patient evolution are often accompanied by rich structured information such as demographics, diagnostics and medical exam data. However, current methods do not jointly optimize over structured covariates and time series …
Campfire simplifies sparse training for CNNs, achieving high accuracy with minimal pruning.
problem Training CNNs with sparse weights to maintain high accuracy and robustness.
method Gradual pruning technique with simplified sparsity structure, exploring various tradeoffs.
result Sparse ResNet-50 and ResNet-50 v1.5 achieve 75% top-1 accuracy with 70% sparsity, <1% accuracy loss.
Improved classifier accuracy by using more of the class-specific structure in trained models.
problem Softmax ignores valuable information encoded in the full array of class response distributions.
method Developed a hybrid classifier (Softmax-Pooling Hybrid, SPH) that uses Softmax on high-scoring samples and a log-likelihood method on low-scoring samples. result Reduces test set error by 6% to 23% using the exact same trained model.
Problems in machine learning (ML) can involve noisy input data, and ML classification methods have reached limiting accuracies when based on standard ML data sets consisting of feature vectors and their classes. Greater accuracy will require incorporation of prior structural information on data into learning. We study …
ShotgunCSP predicts crystal structures using machine learning, achieving high accuracy with minimal computation.
problem Predicting stable or metastable crystal structures of large systems.
method Noniterative screening using transfer learning and generative models.
result ShotgunCSP achieves 93.3% accuracy in benchmark tests with 90 different crystal structures.
AutoCompress automatically prunes DNNs to ultra-high compression rates without accuracy loss.
problem Efficiently compressing deep neural networks to reduce storage and computation requirements.
method Automatic hyperparameter determination, ADMM-based structured weight pruning, purification step, heuristic search.
result Achieves ultra-high pruning rates on weights and FLOPs, up to 33x in pruning rate.
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.
Extends binary data classification for hierarchical data.
problem Efficiently classify data with hierarchical class labels.
method Extends a simple binary data classification approach to handle hierarchical relationships.
result Shows computational and accuracy advantages in certain settings.
MRPC improves causal graph inference in R with better accuracy.
problem Accurate inference of causal graphs from data.
method Improves the PC algorithm with online FDR control, v-structure identification, and robust correlation estimation.
result Significantly reduces false positive edges and accurately identifies v-structures.
We examine a class of embeddings based on structured random matrices with orthogonal rows which can be applied in many machine learning applications including dimensionality reduction and kernel approximation. For both the Johnson-Lindenstrauss transform and the angular kernel, we show that we can select matrices yield…
We introduce a new spatial data structure for high dimensional data called the \emph{approximate principal direction tree} (APD tree) that adapts to the intrinsic dimension of the data. Our algorithm ensures vector-quantization accuracy similar to that of computationally-expensive PCA trees with similar time-complexity…
Efficient RNNs on FPGA using structured matrices improve energy efficiency 35.7x.
problem Irregular network structure after pruning degrades RNN performance and energy efficiency.
method Use block-circulant matrices to compress and accelerate RNNs in FPGA.
result Achieved maximum energy efficiency improvement of 35.7x compared to ESE.