Paper explores vector embeddings, distributional hypothesis, and PIP loss for natural language processing.
problem Understanding the effect of dimensionality on vector embeddings and their functionality.
method Formulates a theoretical framework, proposes PIP loss, and reveals bias-variance trade-off.
result Discovers robustness and forward stability of vector embeddings, answers dimensionality selection problem.
Paper explains word embedding dimensionality and proposes a new metric.
problem Understanding the optimal dimensionality of word embeddings.
method Proposed Pairwise Inner Product (PIP) loss to measure dissimilarity.
result Revealed a bias-variance trade-off in dimensionality selection.
Paper proposes PiPs for non-stationary 1D signal analysis.
problem Handling non-stationary oscillatory data in signal analysis.
method Kernel-based optimization using Gaussian Process and Pattern-inducing Points (PiPs).
result PiPs improve signal reconstruction accuracy and robustness.
PIP-Net predicts pedestrian crossing intentions with up to 4-second lead.
problem Accurate pedestrian intention prediction for autonomous vehicles in real-world scenarios.
method Recurrent and temporal attention-based model using kinematic and spatial features.
result PIP-Net predicts pedestrian crossing intentions up to 4 seconds in advance.
New sampler reduces MCMC complexity for Bayesian variable selection.
problem High-dimensional Bayesian variable selection with high computation complexity.
method Variable-complexity subset weighted-Tempered Gibbs Sampler (wTGS) with Rao-Blackwellized estimator.
result Variances of Rao-Blackwellized estimator are smaller than those of subset wTGS.
Study analyzes price response and spread impact in foreign exchange markets.
problem Understanding deviations from Markovian behavior in foreign exchange markets.
method Detailed large-scale data analysis of price response functions for different years and time scales, using pip bid-ask spread definition.
result Large pip spreads significantly impact price response in foreign exchange markets.
A new ML framework for efficient probabilistic inference.
problem Efficient and versatile learning with limited data.
method ML-PIP framework and VERSA method for meta-learning probabilistic inference.
result Sets new state-of-the-art results on benchmark datasets.
New GPU-based algorithm for fast optimal transport on brain tractograms.
problem Efficiently comparing and transferring labels in brain tractograms.
method Multiscale algorithm using Sinkhorn divergences on GPU.
result Smooth assignments for label transfer in tractograms.
New method improves conformal prediction for machine learning models.
problem Improving the efficiency and informativeness of conformal prediction models.
method Introduces Penalized Inverse Probability (PIP) and Regularized PIP (RePIP) nonconformity score functions.
result PIP-based conformal classifiers strike a good balance between informativeness and efficiency.
BARMPy offers a Python package for Bayesian Additive Regression Models.
problem Making complex Bayesian models accessible to machine learning practitioners.
method Object-oriented design compatible with SciKit-Learn, documentation and tutorial provided.
result Ease of use and compatibility with existing machine learning tools.
New framework selects high-quality pretraining data without training LLMs.
problem Slow progress in understanding pretraining data due to costly experiments.
method Statistical framework based on perplexity-benchmark correlations.
result Approach outperforms existing methods on multiple benchmarks.
dnamite simplifies NAMs for feature selection and survival analysis.
problem Handling complex machine learning tasks on large-scale data.
method Python package implementing Neural Additive Models (NAMs) for feature selection and survival analysis.
result dnamite provides a scikit-learn style interface for training NAMs.
Signatory calculates signature and logsignature transforms efficiently on CPU and GPU.
problem Efficient computation of signature and logsignature transforms for machine learning.
method CPU and GPU parallelism, backpropagation, efficient precomputation strategies, algorithmic improvements.
result Substantial speedups on CPU and GPU, including real-world applications.
MarkerMap selects key genes for cell type analysis in single-cell RNA-seq.
problem Selecting informative genes from large single-cell RNA-seq datasets is challenging and computationally intensive.
method MarkerMap is a generative model that identifies minimal gene sets explaining cell type variability.
result MarkerMap outperforms existing methods in both supervised and unsupervised marker selection.
Developed Forex trading heuristics with high profit potential.
problem Reduced trade opportunities due to technical indicator values.
method Machine learning simulation of 10 years of Forex data.
result Optimized trade parameters for 118 pips daily profit.
SurvSet offers a repository of 76 T2E datasets for ML benchmarking.
problem Lack of open-source T2E dataset repositories for ML benchmarking.
method Consistent formatting of datasets for various ML algorithms and statistical methods.
result SurvSet provides a comprehensive resource for T2E analysis.
Efficiently differentiate functions of large matrices using new adjoint systems.
problem Differentiating functions of large matrices in scientific and probabilistic machine learning models.
method Deriving and implementing new adjoint systems for Lanczos and Arnoldi iterations in JAX.
result Efficient differentiation of PDEs, Gaussian process models, and Bayesian neural networks.
PyHHMM is a Python library for HHMMs with advanced features.
problem Handling heterogeneous observation models and missing data in HMMs.
method Object-oriented Python implementation with advanced features.
result PyHHMM supports a heterogeneous observation model and missing data inference.
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.
Python package reduces hubness in high-dimensional data.
problem Hubness in high-dimensional data affects machine learning tasks.
method Hubness analysis, reduction, and approximate neighbor search.
result Improves neighbor retrieval and learning tasks in high dimensions.
Model predicts political ideology using context vectors to mitigate bias and scarcity.
problem Scarcity and selection bias in political ideology prediction.
method Proposes a statistical model decomposing embeddings into context and position vectors, training an end-to-end model for deployment.
result Model can predict ideological labels even with minimal biased data, outperforming state-of-the-art methods.
Confidence bands for tuning curves improve hyperparameter comparison in NLP.
problem Ambiguity in comparing hyperparameter tuning methods.
method Constructs exact, simultaneous, and distribution-free confidence bands for tuning curves.
result Confidence bands provide a robust basis for comparing methods rigorously.
A new ICA algorithm robustifies independent component analysis by accounting for group-wise stationary noise.
problem Tackles the challenge of independent component analysis in the presence of group-wise stationary confounding noise.
method Introduces coroICA, a novel ICA algorithm that extends the ordinary ICA model to incorporate group-wise confounding.
result Demonstrates improved performance and robustness of ICA in settings where other methods fail.
New method provides calibrated feature importance explanations for regression models.
problem Lack of uncertainty quantification in existing local explanation methods.
method Extension of Calibrated Explanations method to support regression and probabilistic regression.
result Calibrated Explanations for regression provides quantified uncertainty and robust explanations.
Python package for ordinal regression using gradient boosting.
problem Handling ordinal variables in machine learning.
method Gradient boosting with latent variable framework.
result Performs joint optimization of latent function and threshold vector.
GPry accelerates Bayesian inference for non-Gaussian posteriors.
problem Efficient Bayesian inference for complex models with moderate parameters.
method Generative Gaussian Process surrogate model with SVM classifier, active learning.
result Significant reduction in inference time and computational cost.
Chronicals boosts LLM fine-tuning speed by 3.51x over Unsloth.
problem Memory bottleneck in fine-tuning large language models.
method Four optimizations: fused kernels, cross-entropy reduction, LoRA+, and sequence packing.
result 3.51x speedup on A100-40GB with Qwen2.5-0.5B.
TorchIO simplifies medical image processing for deep learning.
problem Challenges in processing medical images like MRI and CT.
method Efficient loading, preprocessing, augmentation, and patch-based sampling.
result Enables researchers to focus on deep learning experiments.
New metrics fail adversarial tests, with some more robust than others.
problem Evaluation metrics for time-series anomaly detection were improved but not fully robust.
method Adversarial stress-testing of 12 adopted metrics on real benchmarks.
result Some metrics are more robust than others, with ROC-based metrics being gamed more often.
A new loss function α-loss bridges log-loss and 0-1 loss for binary classification.
problem Improving binary classification performance using a tunable loss function.
method Introducing α-loss, proving its margin-based form and classification-calibration, and providing an upper bound on empirical risk. result Empirical and expected risk difference upper bound for logistic regression-based classification.
Introduces Fitzpatrick losses, tighter than Fenchel-Young losses.
problem Improving loss functions for machine learning.
method Introduces Fitzpatrick losses based on the Fitzpatrick function.
result Fitzpatrick losses are tighter than Fenchel-Young losses.
We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise when margin losses can be proper composite losses, explicitly show how to determ…
Tamed Cross Entropy (TCE) loss outperforms standard CE loss in noisy classification tasks.
problem Improving classification performance in noisy data scenarios.
method Introducing Tamed Cross Entropy (TCE) loss, a derivative of Cross Entropy (CE) loss.
result TCE loss outperforms CE loss in all tested noisy classification scenarios.
Unified surrogate loss framework for multi-label learning with strong consistency guarantees.
problem Improving consistency and accounting for label correlations in multi-label learning.
method Introducing multi-label logistic loss and extending it to comprehensive multi-label comp-sum losses, proving strong consistency guarantees for any multi-label loss.
result Unified surrogate loss framework benefiting from strong consistency guarantees for any multi-label loss.
This paper introduces new loss functions for balanced multi-class classification.
problem Balancing class imbalance in multi-class classification.
method Introduces two new surrogate loss families: GLA and GCA.
result GCA losses offer stronger theoretical guarantees in imbalanced settings.
Visualizes basins of attraction for neural network loss functions.
problem Understanding the nature of neural network loss surfaces and basins of attraction.
method Gradient-based random sampling to visualize basins of attraction and stationary points.
result Entropic loss has a more searchable landscape with fewer stationary points than quadratic loss.
This work broadens calibeating to various proper losses using Bregman divergence.
problem Calibration for a wide range of proper losses.
method Regret minimization and Bregman divergence approach.
result U-calibration results for a family of Tsallis losses with logarithmic regret and dimension independence.
This work generalizes calibeating for a broader range of proper losses using Bregman divergence.
problem Calibration for a wide range of proper losses beyond Brier and log loss.
method Regret minimization based on Bregman divergence for a family of proper losses.
result U-calibration results for a family of Tsallis losses with logarithmic regret and dimension independence.
Proposes squentropy loss for improved classification accuracy and model calibration.
problem Theoretical and empirical evidence for cross-entropy loss is lacking.
method Introduces squentropy loss as the sum of cross-entropy and average square loss over incorrect classes.
result Squentropy loss outperforms cross-entropy and rescaled square losses in classification accuracy and model calibration.
New loss function calibrates WW-hinge loss for multiclass SVM.
problem WW-hinge loss not calibrated with 0-1 loss.
method Introduced ordered partition loss and proved WW-hinge loss is calibrated.
result WW-hinge loss is calibrated with ordered partition loss.
The study analyzes a model for aggregate losses with dependent and overdispersed inter-losses times.
problem Analyzing aggregate loss models with dependent and overdispersed inter-losses times.
method The study uses a two-state Markovian arrival process (MAP2) and a Markov renewal process to model the inter-losses times. Severities are modeled using a heavy-tailed, double-Pareto Lognormal distribution. The model is estimated via direct maximization of the likelihood function.
result The model with dependence and overdispersion in inter-losses times leads to higher capital charges compared to a Poisson process.
Logitron combines Perceptron and logistic loss for improved classification.
problem Non-convex and non-smooth zero-one loss function in classification models.
method Introduces a Perceptron-augmented convex classification framework with an extended logistic loss function.
result Hinge-Logitron outperforms logistic regression and SVM in classification accuracy.
Symmetric losses improve classifier robustness from corrupted labels.
problem Improving classifier performance from corrupted labels.
method Symmetric losses that satisfy a certain condition.
result Symmetric losses enhance robust classification from corrupted labels.
Two new algorithms improve performance in adversarial bandits with unbounded losses.
problem Adversarial Multi-Armed Bandits with unbounded losses.
method Developed UMAB-NN and UMAB-G for non-negative and general unbounded losses respectively.
result UMAB-NN achieves the first adaptive and scale-free regret bound for non-negative unbounded losses.
Paper explores connections between loss functions and consistency in binary classification and regression.
problem Consistency in binary classification and regression applications.
method Characterization of conformable loss functions and derivation of a new Huber-type loss function.
result Margin-based loss functions are equivalent to loss functions of squared standardized logistic regression residuals.
Paper introduces a new topological loss for better convergence.
problem Optimizing topological losses for model's desired topological behavior.
method Introduces a new regularized topology-aware loss function.
result Guarantees efficient optimization of the new loss function.
Novel loss functions improve decision tree learning from noisy data.
problem Training decision trees with noisy labels.
method Introducing distribution losses and a new negative exponential loss.
result The negative exponential loss leads to efficient and robust decision tree learning.
Theoretical analysis of cross-entropy loss functions and their robustness.
problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First H-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.