arXiv Machine Learning
Jun 15
Ensembling Sparse Autoencoders
arXiv:2505. 16077v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features.
Reducing Learner Redundancy in Boosting via Residual Orthogonalization
arXiv:2606. 17567v1 Announce Type: new Abstract: While sequential residual fitting is the bedrock of standard boosting frameworks, it inherently breeds learner redundancy by repeatedly revisiting correlated error components.
Related stories
arXiv Machine Learning
Jul 13
Spectrally Deconfounded Gradient Boosting
arXiv:2607. 09371v1 Announce Type: cross Abstract: Flexible machine-learning methods can be sensitive to hidden confounding: they may learn associations induced by unobserved confounders rather than stable signals.
arXiv AI
Jun 30
Counterfactual Residual Data Augmentation for Regression
arXiv:2606. 28460v1 Announce Type: cross Abstract: Data-driven modeling in real-world regression tasks often suffers from limited training samples, high collection costs, and noisy observations.
arXiv Machine Learning
Aug 5
Double Descent in Gradient Boosting Decision Trees via Split-Candidate Scaling
arXiv:2608. 03111v1 Announce Type: new Abstract: Double descent is commonly studied by scaling an explicit capacity parameter, such as neural-network width.
arXiv Machine Learning
Jun 18
PACT: Preserving Anchored Cores in Task-vectors for Model Merging
arXiv:2606. 18627v1 Announce Type: new Abstract: Model merging has emerged as a training-free alternative to multi-task learning, aiming to combine multiple task-specific fine-tuned models into a single multi-task model.
arXiv AI
Jun 16
ALCL: An Adaptive Log-Correntropy Loss for Robust Learning under Non-Gaussian Noise
arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.
arXiv Machine Learning
Jul 14
Vertical Fusion: Condensing Internal Representations for Robust ViT Classification
arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.
Hugging Face Trending Papers
Aug 4
Double Descent in Gradient Boosting Decision Trees via Split-Candidate Scaling
Double descent is commonly studied by scaling an explicit capacity parameter, such as neural-network width. For gradient boosting decision trees (GBDTs), however, an analogous single-axis capacity parameter has not been established.
arXiv AI
Jun 15
Simplex-Constrained Sparse Bagging: Transitioning from Uniform Priors to Sparse Posteriors in Ensemble Learning
arXiv:2606. 13589v1 Announce Type: cross Abstract: We present Simplex-Constrained Sparse Bagging (SCSB), a mathematically rigorous framework for post-training compression and probability calibration of bootstrap-based bagging ensembles.
Hugging Face Trending Papers
Jul 20
Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning
Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch, pre-trained model (PTM) can easily adapt to a new task with fine-tuning.
arXiv Machine Learning
Jun 4
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
arXiv:2606. 05165v1 Announce Type: new Abstract: Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data.
arXiv Machine Learning
Jul 16
Parallel gradient boosting for flexible estimation of conditional distributions
arXiv:2607. 13550v1 Announce Type: cross Abstract: Boosting is one of the most successful learning techniques for standard classification and regression tasks.