New methods correct spectral distortions using known analyte concentrations.
problem Distorted spectral shapes from absorbing and scattering contributions.
method Modified penalized baseline correction methods that incorporate known analyte concentrations.
result Improved prediction performance on near infra-red data sets.
Paper finds Dutch Draw optimal baseline for binary classification.
problem Need a proper baseline for binary classification validation.
method Examined all input-independent baseline methods.
result Dutch Draw is optimal baseline under given conditions.
Paper uses tensor completion to estimate HVAC fan power baselines.
problem Estimating HVAC fan power without demand response.
method Tensor completion for multi-dimensional data analysis.
result Tensor completion outperforms existing baselining methods.
A new baseline for Shapley values in MLPs considers model use.
problem Lack of a robust baseline for Shapley values in neural networks.
method Proposes a neutrality-based baseline for Shapley values.
result Empirically validated the proposed baseline for binary classification tasks.
Enhanced visual feature attribution via adaptive baseline weighting.
problem IG's sensitivity to baseline images leads to noisy or unstable explanations.
method Weighted Integrated Gradients (WG) evaluates and weights baselines for improved reliability.
result WG improves over Expected Gradients (EG) by up to 36% across various models.
Bayesian Deep Learning experiments often use weak baselines, leading to misleading conclusions.
problem Misleading conclusions in Bayesian Deep Learning due to weak baselines in experiments.
method Used a fixed number of iterations for baselines and compared them with models trained to convergence.
result Monte Carlo dropout baseline outperforms or performs competitively with superior methods.
Paper presents a universal baseline for binary prediction models.
problem Need a robust baseline to evaluate model performance.
method Dutch Draw (DD) baseline method for binary classification models.
result Reduces to almost always predicting zero or one in most situations.
Action-dependent baselines do not reduce variance in reinforcement learning.
problem The effectiveness of action-dependent baselines in reducing variance and improving sample efficiency in reinforcement learning.
method Decomposed the variance of the policy gradient estimator and reviewed the implementation details of prior papers.
result Action-dependent baselines do not reduce variance over a state-dependent baseline in commonly tested benchmark domains.
Bayesian Scattering offers a simple baseline for image data uncertainty.
problem Lack of interpretable, mathematically grounded uncertainty quantification methods for image data.
method Coupling wavelet scattering transform with a simple probabilistic head.
result Bayesian Scattering provides sensible uncertainty estimates under distribution shifts.
Proposes a new method to interpret EEG classification models without needing a baseline.
problem Reliable interpretation of EEG classification models using integrated gradients.
method Compensated Integrated Gradients using Shapley sampling.
result The proposed method provides more reliable attributions than original integrated gradients.
Action-dependent baselines reduce policy gradient variance in deep RL.
problem High variance in policy gradient methods, especially in long-horizon or high-dimensional action spaces.
method Derive a bias-free action-dependent baseline that fully exploits policy structure without additional assumptions.
result Demonstrates and quantifies the benefit of action-dependent baselines through theoretical and numerical results.
We reduce variance in RL with input-dependent baselines.
problem High variance in RL with standard baselines in input-driven environments.
method Derive and use a bias-free, input-dependent baseline; propose a meta-learning approach.
result Input-dependent baselines improve training stability and policy quality.
Study shows popular RL methods are inefficient due to unfair baselines.
problem Data inefficiency in deep reinforcement learning for Atari.
method Used modified DQN as a baseline to show actual improvements.
result Popular RL methods are inefficient due to unfair baselines, not new techniques.
An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and analyze a new model-based approach to compute a safe policy when we have access …
Paper compares two local explanation methods for machine learning models.
problem Comparing two local explanation methods for machine learning models.
method Integrated Gradients and Baseline Shapley methods.
result Additional insights on comparative behavior for tabular data and neural networks.
Proposes baselines for joint NAS and HPO optimization.
problem Joint optimization of neural architecture and hyperparameters for multiple objectives.
method Extends existing methods to jointly optimize with multiple objectives.
result Serves as simple baselines for future multi-objective joint NAS + HPO research.
A training-free conformal interval is a mandatory baseline for probabilistic time-series forecasting.
problem Comparing probabilistic forecasters against weak or omitted baselines.
method A simple conformal interval with no parameters and no training.
result The ConformalNaive interval decisively beats several baselines.
Method predicts brain structure progression in Alzheimer's from baseline MRI.
problem Predicting longitudinal brain structure changes in Alzheimer's disease.
method Large deformation diffeomorphic metric mapping (LDDMM) with personalized trajectories.
result Method successfully predicts brain structure changes from baseline data.
Bayesian method detects neuron spike activities from noisy fluorescence data.
problem Detecting neuron spike activities from noisy fluorescence data.
method Random finite set (RFS) based Bayesian approach.
result Gains 12% extra detection accuracy compared to MLSpike method.
Paper identifies problematic baselines in Shapley value explanations and proposes a reweighting mechanism.
problem Identifying and addressing the suboptimality of baselines in Shapley value feature importance analysis.
method Analyzed suboptimality of baselines, identified problematic baseline, generalized uninformativeness, and designed a reweighting mechanism.
result Proposed uncertainty-based reweighting mechanism effectively accelerates computation and improves explanation quality.
SPIBB improves safe policy improvement with a softer baseline approach.
problem Improving policies safely in reinforcement learning.
method Baseline Bootstrapping algorithm (SPIBB) that allows policy search over a wider set of policies, controlling policy change according to local model uncertainty.
result Significant improvement in safe policy improvement over existing methods.
Enhances survival analysis by separating population behavior from individual dynamics.
problem Improving the training and inference of survival analysis models for sparsely occurring events.
method Decouples survival analysis into an aggregated baseline hazard and independent survival scores.
result Achieves competitive performance and robust results without fine-tuning.
Simple graph representation outperforms complex methods in graph classification.
problem Graph classification and representation learning on graphs.
method Developed a simple yet meaningful graph representation and tested its effectiveness.
result Simple graph representation achieves similar performance to state-of-the-art methods for non-attributed graph classification.
Paper improves safe policy improvement with estimated baseline policy.
problem Unreliable batch Reinforcement Learning algorithms in real-world applications.
method Apply SPIBB algorithms with an estimated baseline policy.
result Safe policy improvement guarantees over true baseline without direct access.
Efficiently approximates time series correlation using Fourier transform and neural networks.
problem Efficiently approximating correlation in time series data.
method Embeds time series into a low-dimensional Euclidean space using Fourier transform and neural networks, ensuring accurate correlation approximation from Euclidean distance.
result Our method reduces approximation loss by half and improves top-k correlation search precision from 5% to 20%. Paper recommends baselines for comparing GP approximations.
problem Lack of clear recommendations for comparing GP approximations.
method Developed a training procedure for the variational method of Titsias [2009].
result Variational method is a strong baseline that meets the recommended specification.
GNN-FiLM uses feature-wise linear modulation to improve graph neural networks.
problem Improving graph neural networks for better performance.
method Feature-wise linear modulation applied to target node representations in GNNs.
result GNN-FiLM outperforms baseline methods on a regression task for molecular graphs.
Improves policies with high certainty, even in small samples.
problem Ensuring new policies are better than the baseline with high probability.
method Leverages powerful safety tests and multiple testing for threshold policies.
result Controls the rate of adopting a worse policy to pre-specified error level.
Efficiently trains autoencoders for collaborative filtering on large datasets.
problem Training autoencoders on large, sparse implicit feedback datasets.
method Mini-batch based negative sampling for large-scale training.
result Shows improved performance compared to state-of-the-art baseline models.
The paper evaluates classic tri-training methods for neural semi-supervised learning under domain shift.
problem Difficulty in comparing neural models for domain shift learning.
method Proposes a novel multi-task tri-training method to reduce complexity.
result Classic tri-training with additions outperforms state-of-the-art methods.
EC3 combines clustering and classification for better ensemble learning performance.
problem Combining classification and clustering for improved prediction performance.
method EC3 merges classification and clustering using an optimization function and block coordinate descent.
result EC3 outperforms other methods by at most 10% in AUC on 13 benchmark datasets.
New method detects OOD samples using neural network trajectories.
problem Lack of comprehensive layer exploration in OOD detection.
method Functional data perspective, analyzing sample trajectories through multi-layer classifier.
result Empirically validated as effective compared to state-of-the-art methods.
Paper formalizes continual semi-supervised anomaly detection, showing promising results.
problem Formalizing continual semi-supervised anomaly detection in real-world conditions.
method Baseline model of variational autoencoder (VAE) with deep generative replay and outlier rejection.
result Outlier rejection shows promising results, often surpassing baseline methods.
Few-shot learning benchmarks can be solved without using support set labels at test-time.
problem Evaluate the adequacy of few-shot learning benchmarks that require task supervision at test-time.
method Introduced Centroid Networks, a modification of Prototypical Networks, which hides support set labels from the method at test-time and uses clustering to recover them.
result Most benchmarks cannot be solved perfectly without LT, indicating the inadequacy of benchmarks requiring task supervision.
The study introduces backward baselines to distinguish past prediction from future prediction in machine learning models.
problem Differentiating between past and future prediction in machine learning models.
method Theoretical, empirical, and normative arguments support a family of simple and efficient statistical tests called backward baselines.
result The study provides a meaningful backward baseline for auditing black-box prediction systems.
IPO optimizes reinforcement learning with constraints for better performance.
problem Maximizing long-term reward while satisfying cumulative constraints in decision problems.
method Interior-point Policy Optimization (IPO) using logarithmic barrier functions.
result IPO outperforms state-of-the-art baselines in reward maximization and constraint satisfaction.
Predict and classify brain image evolution trajectories from a single MRI timepoint.
problem Diagnosing early mild cognitive impairment (eMCI) from a single MRI scan.
method Supervised and unsupervised learning frameworks that predict and label intensity patch evolution trajectories from a baseline MRI.
result Classification accuracy increased by up to 10% points compared to single timepoint-based methods.
A simple baseline outperforms deep learning methods in transportation forecasting.
problem The importance of stationarity and recurrent patterns in transportation data.
method A naive baseline based on average weekly patterns and linear regression.
result The baseline method achieves comparable or better results than state-of-the-art deep learning approaches.
PCKID kernel improves spectral clustering on incomplete data.
problem Handling incomplete data in spectral clustering.
method Combining posterior distributions of Gaussian Mixture Models on different scales.
result PCKID kernel outperforms baseline methods for all fractions of missing values.
Algorithm safely learns from sub-optimal baseline policies while satisfying constraints.
problem Safe reinforcement learning with constraints when baseline policy is sub-optimal.
method Iterative policy optimization alternating between return maximization, baseline distance minimization, and constraint projection.
result Consistently outperforms baselines, achieving 10x fewer constraint violations and 40% higher reward.
Sever robustifies machine learning methods to handle outliers.
problem Machine learning methods are brittle to structured outliers in high dimensions.
method A meta-algorithm that hardens base learners to resist outliers.
result Sever achieves significantly greater robustness than baselines in drug design and spam classification datasets.
Bayesian algorithm detects changes in fluctuating baselines.
problem Detecting change points in time series with a shifting baseline.
method Extended Bayesian online change point detection (BOCPD) algorithm.
result The extended algorithm can detect changes in fluctuating baselines.
New method FedEx accelerates federated hyperparameter tuning.
problem Federated hyperparameter tuning challenges in distributed learning.
method FedEx method connecting to weight-sharing, adapted for federated optimization.
result FedEx outperforms natural baselines on various benchmarks.
Enhances adversarial examples' transferability through diverse input patterns.
problem Low success rates of adversarial attacks in the black-box setting.
method Applying random transformations to input images at each iteration.
result Generates adversarial examples that transfer better to different networks.
Simple tabular event prediction model outperforms existing methods.
problem Predicting events from tabular data with historic events.
method Standard autoregressive LLM-style transformers with elementary positional embeddings and causal language modeling.
result Simple model outperforms existing approaches across various datasets and use-cases.
New approach to avoid bad incentives in reinforcement learning agents.
problem Designing safe reinforcement learning agents that avoid unnecessary disruptions.
method Break down side effects penalties into baseline state and deviation measure; introduce new stepwise inaction baseline and relative reachability deviation measure.
result Combination of new design choices avoids undesirable incentives, while simpler alternatives fail.
This research secures deployed sentiment analysis models by identifying and defending against attack vectors.
problem Securing deployed machine learning models, particularly sentiment analysis systems, from adversarial attacks.
method BAD (Build, Attack, Defend) Architecture, evaluating two implementations.
result Demonstrated a viable methodology for securing machine learning models in production.
O-MedAL optimizes medical image analysis with online active deep learning.
problem Improving accuracy in medical image analysis with limited labeled data.
method Online Active Deep Learning method that queries examples maximizing average distance to training set.
result Significant performance improvements, including 6.30% accuracy boost with 25% labeled data.