Machine learning enhances cardiac arrhythmia treatment through predictive modelling.
problem Improving catheter ablation success rates for treating atrial fibrillation.
method Combining machine learning and predictive modelling with cardiac electrophysiology data.
result Enhanced accuracy in predicting and inferring parameters of cardiac models.
We consider the problem of locating a point-source heart arrhythmia using data from a standard diagnostic procedure, where a reference catheter is placed in the heart, and arrival times from a second diagnostic catheter are recorded as the diagnostic catheter moves around within the heart. We model this situation as a …
Random forest models predict CLABSI risk in hospital admissions, with static models performing similarly to dynamic ones.
problem Predicting CLABSI risk in hospital admissions using EHR data with competing risks.
method Comparison of static and dynamic random forest models for binary, multinomial, survival, and competing risks outcomes.
result Static and dynamic random forest models perform similarly in predicting CLABSI risk, with multinomial models having the lowest computation times.
Study ablated data augmentation techniques and their mathematical equivalence to penalties.
problem Lack of mathematical understanding of differences between ablated data augmentation techniques.
method Formal model of mean ablated data augmentation and inverted dropout for linear regression; empirical validation for deep networks.
result Ablated data augmentation and inverted dropout are mathematically equivalent to penalties in optimization.
Ablation studies show BCF model's propensity score is not essential for treatment effect estimation.
problem Understanding the necessity of propensity score in nonparametric treatment effect estimation.
method Partial ablation studies of Bayesian Causal Forest (BCF) model.
result Excluding estimated propensity score does not affect treatment effect estimation or uncertainty quantification.
The study measures feature importance in models by randomly ablating features and averaging loss changes.
problem Measuring feature importance in machine learning models.
method Randomly ablating features and averaging loss changes over many points and replacements.
result Uncertainty measures of feature importance are presented.
This paper uses deep learning to estimate flow fields from OCT images for laser ablation control.
problem Automatic control of laser bone ablation using 4D OCT images.
method Semi-supervised convolutional neural network for 2.5D scene flow estimation.
result Scene flow estimation enables markerless tracking and automated laser ablation control.
ABC method analyzes diffusion model dependence without retraining.
problem Difficulties in characterizing diffusion models' dependence on training data.
method Ablation-based counterfactuals using model components trained on different splits.
result Demonstrates limits of training data attribution and existence of unattributable samples.
New method certifies robustness to sparse adversarial attacks.
problem Ensuring robustness of classifiers to sparse adversarial attacks.
method Randomized ablation of input features to provide robustness guarantees.
result Certifies robustness to sparse adversarial attacks with up to 31 pixels of distortion.
In this work, we investigate the use of three information-theoretic quantities -- entropy, mutual information with the class variable, and a class selectivity measure based on Kullback-Leibler divergence -- to understand and study the behavior of already trained fully-connected feed-forward neural networks. We analyze …
TSFMs show redundant components in layers, affecting their performance.
problem Redundant components in TSFMs layers impact their predictive accuracy.
method Mechanistic interpretability tools, ablations, logit attribution, theoretical framework.
result TSFMs are robust to ablations of entire layers and specific heads.
LSTM-FCN and ALSTM-FCN improve time series classification performance.
problem Improving time series classification performance.
method Ablation tests on LSTM-FCN and ALSTM-FCN, comparing z-normalizing techniques, dimension shuffle impact, and GRU replacement.
result LSTM and FCN blocks perform better together, and z-normalizing the whole dataset is more effective.
New framework improves offline RL performance without complex methods.
problem Limited access to online interactions in real-world RL applications.
method Behavior Regularized Actor Critic (BRAC) framework.
result Many recent technical complexities are not necessary for strong offline RL performance.
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
problem Quadratic complexity of transformers limits long-context reasoning in resource-constrained systems.
method Hydra uses a modular architecture with adaptive routing between sparse global attention, mixture-of-experts, and dual memories.
result Hydra achieves significant throughput and accuracy improvements for long-context reasoning.
New dataset tests mental rotation from single images, improving model understanding of 3D scenes.
problem Understanding how a scene looks from a different viewpoint using a single image.
method Created CLEVR-MRT dataset, explored neural architectures for volumetric scene representations.
result Demonstrated the effectiveness of volumetric representations in answering mental rotation questions.
ECP optimizes expensive functions without knowing Lipschitz constant.
problem Optimizing expensive, non-convex functions with unknown Lipschitz constants.
method ECP minimizes evaluations by focusing on potentially optimal regions, eliminating Lipschitz constant estimation.
result Guaranteed no-regret performance and minimax-optimal regret bounds.
Predicts stock volatility using Twitter data and random forests.
problem Predicting stock implied volatility using Twitter data.
method Random forests with ablation study on different predictors, including Twitter attention and sentiment features.
result Certain sectors like Consumer Discretionary, Technology, Real Estate, and Utilities are easier to predict.
Deep learning improves forensic matching of casings.
problem Identifying if two casings came from the same firearm.
method Contrastive neural networks trained on casings dataset.
result Contrastive learning achieved better ROC AUC than CMC.
GCN model fails to match KG entities as expected.
problem Entity alignment in Knowledge Graphs using GCN.
method Used Graph Convolutional Network (GCN) for entity alignment in KGs.
result Implementation of GCN model differs from original paper, requiring additional tricks.
Method generates anatomically-controllable medical images with segmentation guidance.
problem Challenging to enforce anatomical constraints in generated medical images.
method Segmentation-guided diffusion models with random mask ablation training.
result New state-of-the-art in faithfulness to input anatomical masks.
Double descent phenomenon explained in simple terms.
problem Understanding the surprising drop in test error in overparameterized models.
method Informal explanation using linear algebra and probability, visual intuition with polynomial regression, mathematical analysis with ordinary linear regression.
result Three factors create double descent: data undersampling, model size, and parameter count. Ablating any one of these factors prevents double descent.
IGSD separates task-specific content channels in transformer components by comparing activation replacement with zero ablation.
problem Mechanistic interpretability of transformer components
method IGSD: paired-intervention framework for comparing activation replacement with zero ablation
result IGSD identifies an early-layer content channel in transformer components that standard importance methods underestimate.
CIT and CIF improve feature selection for downstream prediction.
problem Feature selection bias in machine learning models.
method Conditional inference trees and forests with Bonferroni correction.
result CIF ranks top 3 among 18 regression methods and top 4 among 17 classification methods.
Paper proposes forecast-necessity testing for accurate causal interpretation in nonlinear time-series models.
problem Misinterpretation of causal scores from nonlinear models as regression coefficients.
method Systematic edge ablation and forecast comparison to evaluate causal necessity.
result Causal relationships with similar scores can differ in their necessity for accurate prediction.
Embedding-based Knowledge Base Completion models have so far mostly combined distributed representations of individual entities or relations to compute truth scores of missing links. Facts can however also be represented using pairwise embeddings, i.e. embeddings for pairs of entities and relations. In this paper we ex…
SEF-M improves spiking neural network classification accuracy by 14%.
problem Improving spiking neural network classification accuracy.
method Meta-neuron based learning algorithm with time-varying weight model.
result Time-varying weight model improves classification accuracy by 14%.
Model identifies order splitting and liquidity replenishment as necessary for the square-root law of market impact.
problem Quantifying the square-root law of market impact and identifying its underlying mechanisms.
method Minimal limit-order-book model with heterogeneous interacting agents calibrated against real data. Counterfactual ablation to isolate mechanisms.
result Order splitting and liquidity replenishment are necessary for the square-root law of market impact.
INFERS PDEs from data samples using learned context.
problem Inferring explicit PDEs from unseen dynamics.
method Contextual Finite Differences (CFD) method integrating PDE form and differential scheme.
result Yields a PDE fitting the data sample for signal prediction and explanation.
Model separates overall uncertainty into aleatoric and epistemic components for active learning.
problem Active learning with uncertainty quantification.
method Non-stationary Heteroscedastic Gaussian process model.
result Model separates overall uncertainty into aleatoric and epistemic components.
Improved electrical load forecasting model using Fourier-enhanced RNN.
problem Electrical load time series downscaling with high accuracy and low error.
method Combines recurrent neural network with Fourier seasonal embeddings and self-attention.
result Significantly reduces RMSE across different time horizons compared to existing methods.
GrowNet uses shallow neural networks for gradient boosting, outperforming existing methods.
problem Improving gradient boosting performance through shallow neural networks.
method Unified gradient boosting framework with shallow neural networks as weak learners, incorporating corrective steps.
result GrowNet outperformed state-of-the-art boosting methods in classification, regression, and learning to rank tasks.
Review of integrating Bayesian methods with neural network-based MPC.
problem Lack of standardized benchmarks and reliable analyses in Bayesian MPC.
method Systematic analysis of Bayesian methods in neural-network-based MPC.
result Need for standardized benchmarks, ablation studies, and transparent reporting.
Efficient neural network optimization reduces costs and improves model performance.
problem High computational costs in optimizing neural networks, especially at scale.
method Introduces self-attentive feed-forward neural units (SAFFU) for efficient optimization.
result Explicit solutions outperform models optimized by backpropagation alone, and further training with backpropagation leads to better optima from smaller data sets.
In this paper we study the problem of acoustic scene classification, i.e., categorization of audio sequences into mutually exclusive classes based on their spectral content. We describe the methods and results discovered during a competition organized in the context of a graduate machine learning course; both by the st…
Aims to create a world model without baggage, achieving good performance.
problem Creating world models without baggage and limitations.
method Self-supervised representation learning, frame and action stacking, data augmentation.
result Good performance on the Atari 100k benchmark.
New insights into training deep networks with low rank layers.
problem Efficiency in training deep neural networks.
method Analysis of techniques for training in low rank space.
result Falsified common beliefs in training deep networks.
LSTMs were introduced to combat vanishing gradients in simple RNNs by augmenting them with gated additive recurrent connections. We present an alternative view to explain the success of LSTMs: the gates themselves are versatile recurrent models that provide more representational power than previously appreciated. We do…
Sparse point observations can provide useful local constraints, but their benefit for radar-like fields depends on the training loss, uncertainty representation, and how observation support is encoded in the model.
problem Improving dense radar-field forecasts with sparse point observations
method A multimodal graph neural network nowcasting system over the Nordic radar domain
result Each source improves a different part of the forecast problem
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation. FiLM layers influence neural network computation via a simple, feature-wise affine transformation based on conditioning information. We show that FiLM layers are highly effective for visual reasoning - an…
Optimizes neural networks by removing unnecessary layers, improving performance and speed.
problem Finding the optimal depth of neural networks to improve performance and speed.
method Develops a fast end-to-end method for training lightweight neural networks with multiple classifier heads, allowing the model to determine the importance of each head and choosing a single shallow classifier.
result Significantly reduces the number of parameters and accelerates inference, outperforming many standard pruning methods.
MixBoost generates synthetic instances to balance imbalanced datasets.
problem Training models on imbalanced datasets.
method Iterative data augmentation method that selects and combines instances from majority and minority classes.
result MixBoost outperforms existing approaches on 20 benchmark datasets.
Capsule networks improve with dynamic routing using Wasserstein objective.
problem Capsule networks struggle to consistently outperform traditional neural networks.
method Dynamic routing scheme using approximate Wasserstein objective to select capsules.
result Capsule network achieves over 1.2% improvement on CIFAR-10 with fewer parameters.
In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked …
A new method combines multiple bounds and betting strategies for selective prediction, improving risk coverage in data-scarce settings.
problem Selective prediction with risk control in data-scarce domains.
method Combines concentration inequalities, multiple-testing corrections, and betting-based confidence sequences.
result Transfer-Informed Betting achieves tighter bounds and better coverage in data-scarce settings.
VAR-GPs solve continual learning by updating posteriors sequentially.
problem Catastrophic forgetting in sequential learning tasks.
method Sparse inducing point approximations and auto-regressive variational distribution.
result VAR-GPs prevent catastrophic forgetting and outperform baselines.
Colored noise improves neural network robustness against adversarial attacks.
problem Vulnerability of neural networks to adversarial perturbations.
method Injection of colored noise into network weights and activations during adversarial training.
result Our approach outperforms previous methods in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets.
Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and large amounts of data, a common practice is to download models pre-trained on standard datasets and fine-tune them for specific application doma…
Formalizes and generalizes meta-learning patterns in deep and reinforcement learning.
problem Nested optimization problems in deep and reinforcement learning.
method Formalizes and proves requirements for a shared meta-learning pattern (GIMLI), derives a general-purpose algorithm, and provides a library.
result Demonstrates practical applications and ablation studies of the meta-learning framework and library.