The paper studies Lipschitz equivalence of self-similar sets and their augmented trees.
problem Lipschitz equivalence of self-similar sets and their boundaries.
method Introducing simple augmented trees and using combinatorial devices to show Lipschitz equivalence.
result Lipschitz equivalence of self-similar sets and their boundaries.
In [9] Kaimanovich introduced the concept of augmented tree on the symbolic space of a self-similar set. It is hyperbolic in the sense of Gromov, and it was shown in [13] that under the open set condition, a self-similar set can be identified with the hyperbolic boundary of the tree. In the paper, we investigate in det…
Attention augments forest for tabular data accuracy.
problem Training tabular data models with high accuracy and efficiency.
method Tree Attention Block (TAB) in differentiable forest framework.
result Attention augmented differentiable forest achieves comparable and sometimes higher accuracy than GBDT models.
FAST-DAD distills complex ensemble models into faster, more accurate individual models.
problem Deploying complex AutoML ensemble predictors on tabular data is slow, large, and opaque.
method Data augmentation strategy based on Gibbs sampling from a self-attention pseudolikelihood estimator.
result FAST-DAD distillation produces significantly better individual models than standard training.
Two new Hie-TAN and Hie-TAN-Lite algorithms improve TAN for hierarchical feature spaces.
problem Learning dependencies in hierarchical feature spaces.
method Exploits hierarchical parent-child relationships as constraints to learn a dependency tree.
result Hie-TAN-Lite outperforms Hie-TAN and other methods in predictive accuracy.
CMT efficiently manages memory by inserting and querying memories in logarithmic time.
problem Managing large memory stores efficiently for quick access and updates.
method Designing a Contextual Memory Tree (CMT) that inserts and retrieves memories in logarithmic time.
result CMT improves classification algorithms and image-captioning tasks, demonstrating better computational efficiency.
Enhances time-series regression trees with latent factors for robust financial analysis.
problem Handling predictors with measurement error, trends, seasonality, and missing data.
method Integrates latent stationary factors extracted via state-space methods into time-series regression trees.
result Factor-augmented trees provide a reliable approach for macro-finance problems, exemplified by the lead-lag effect between equity volatility and the business cycle.
Framework explains how dual deep networks learn features from unlabeled data.
problem Understanding self-supervised learning with dual deep networks.
method Theoretical framework and hierarchical latent tree model.
result Deep ReLU networks learn latent variables through contrastive SSL.
In order to investigate the breast cancer prediction problem on the aging population with the grades of DCIS, we conduct a tree augmented naive Bayesian network experiment trained and tested on a large clinical dataset including consecutive diagnostic mammography examinations, consequent biopsy outcomes and related can…
Classifies simple sheaves for knot conormals.
problem Classifying simple sheaves for knot conormals.
method Microsupport classification and correspondence with augmentations.
result Simple sheaves correspond to augmentations, explaining knot contact homology detection.
Simple policy search outperforms advanced learnable test-time augmentation techniques.
problem Improving predictive performance through test-time data augmentation.
method Greedy policy search (GPS) for learning test-time augmentation policies.
result Augmentation policies learned with GPS achieve superior predictive performance and robustness.
We study the fibration of augmented link complements. Given the diagram of an augmented link we associate a spanning surface and a graph. We then show that this surface is a fiber for the link complement if and only if the associated graph is a tree. We further show that fibration is preserved under Dehn filling on cer…
Enhances functional classifier performance with new tree-based methods and unbiased feature importance assessment.
problem Challenges of high-dimensional functional data and biased feature importance assessment.
method Augmented functional classification trees and random forests with ad-hoc conditional permutations for unbiased feature importance.
result Significant enhancement in predictive power of functional classifiers through new feature importance assessment.
New methods use ML predictions to improve statistical inference.
problem Improving statistical inference using machine learning predictions.
method Prediction-Augmented Trees (PART, PAQ) for reliable statistical analysis.
result PART and PAQ outperform existing methods in various datasets.
Proposes a two-stage method for estimating heterogeneous treatment effects using gradient boosting trees.
problem Estimating heterogeneous treatment effects in randomized clinical trials with high-dimensional predictive markers.
method Two-stage statistical learning procedure using gradient boosting trees (XGBoost) to estimate main effects and HTE.
result Improves efficiency in estimating heterogeneous treatment effects through nonparametric function estimation.
We study a natural Lie algebra structure on the free vector space generated by all rooted planar trees as the associated Lie algebra of the nonsymmetric operad (non-Σ operad, preoperad) of rooted planar trees. We determine whether the Lie algebra and some related Lie algebras are finitely generated or not, and prove …
New algorithms learn simple staged trees from data, improving model fit.
problem Complex conditional independences in categorical data vectors.
method Structural learning algorithms for simple staged trees, coalescing the underlying tree.
result Data-learned simple staged trees often outperform Bayesian networks in model fit.
Classifier evasion consists in finding for a given instance x the nearest instance x′ such that the classifier predictions of x and x′ are different. We present two novel algorithms for systematically computing evasions for tree ensembles such as boosted trees and random forests. Our first algorithm uses a Mixe…
Proposes a simple neural network model similar to gradient boosted decision trees.
problem Building a neural network equivalent to gradient boosted decision trees.
method Converts an ensemble of decision trees to a neural network, relaxes properties, and trains a simple neural network model.
result The proposed Hammock model achieves similar performance to gradient boosted decision trees.
GANs generate training data for machine learning tasks.
problem Imbalanced data sets and sensitive information.
method Generative Adversarial Networks (GANs) to create artificial training data.
result A Decision Tree classifier trained on GAN-generated data achieved similar or better accuracy and recall than on original data.
Improved decision tree for big data classification.
problem Classification of large datasets.
method Divide and conquer strategy with decision tree segmentation and leaf level classifier.
result Models are interpretable and as accurate as ensemble methods.
Develops a new model for multi-scale nonlinear dynamics.
problem Interpretable descriptions vs. accurate predictions in modeling nonlinear systems.
method Tree-structured recurrent switching linear dynamical system with Bayesian inference.
result Models offer both interpretability and accuracy in predicting complex dynamics.
Ensemble models improve prediction calibration for mismatched distributions.
problem Calibration issues in deep neural networks with mismatched train and test distributions.
method Simple data augmentation and mixing techniques for ensemble models.
result Improves calibration and accuracy on CIFAR10 and CIFAR100 benchmarks.
Tree-SMU enables strong compositional generalization in neural networks.
problem Zero-shot generalization to novel compositions of concepts.
method Tree Stack Memory Units (Tree-SMU) with Stack Memory Units (SMU).
result Tree-SMU achieves strong empirical results on mathematical reasoning benchmarks.
New method selects facts in proofs using stateful recurrent neural networks.
problem Selecting facts for proving new goals over large formal libraries.
method Stateful architecture based on recurrent neural networks with data augmentation.
result Significantly better performance and solving many new problems compared to previous methods.
Improved VAE model for discrete data through augmented training and multiscale approach.
problem Limited capability of VAE in capturing field correlations in structured data.
method Augmented training with generated variants and multiscale VAE with multiple β values.
result Improved generation quality of VAE models through these methods.
Develops regression trees for estimating cumulative incidence curves in competing risks.
problem Estimating cumulative incidence functions in competing risks settings.
method Uses augmented estimators of the Brier score risk to build and prune regression trees.
result Demonstrates the utility of the proposed methods through simulation studies and real data.
Two methods reduce BN and DNN complexity, balancing size and accuracy.
problem Balancing model size and prediction accuracy in Bayesian networks and deep neural networks.
method Quantization-aware training and tree-augmented naive Bayes structure learning extension.
result Pareto optimal models found for small-scale scenarios.
Combining ensembles and data augmentation harms model calibration.
problem Improving model calibration and robustness with ensembles and data augmentation leads to a trade-off.
method Combining ensemble averaging and data augmentation techniques.
result Combining ensembles and data augmentation can harm model calibration.
Paper proves Łojasiewicz inequalities near simple bubble trees on surfaces.
problem Proving Łojasiewicz inequalities for critical points on surfaces.
method Deriving sufficient conditions for Łojasiewicz inequalities near almost-critical points in a Hilbert space.
result Sequences of almost critical points satisfy Łojasiewicz inequalities as they approach the first non-trivial bubble tree.
GraphACL learns graph representations without augmentation or homophily assumptions.
problem Learning graph representations on heterophilic graphs (nodes with different labels and features).
method Asymmetric Contrastive Learning for Graphs (GraphACL) considers an asymmetric view of neighboring nodes.
result GraphACL significantly outperforms state-of-the-art methods on both homophilic and heterophilic graphs.
SpecAugment improves speech recognition with simple feature augmentation.
problem Improving automatic speech recognition accuracy.
method Applying warping, frequency channel masking, and time step masking to feature inputs of neural networks.
result Achieved state-of-the-art performance on LibriSpeech and Switchboard tasks.
Graph-to-Tree Neural Networks improve structured input-output translation in tasks like semantic parsing and math word problems.
problem Improving performance on tasks like semantic parsing and math word problem solving.
method Graph-to-Tree Neural Networks, consisting of a graph encoder and a hierarchical tree decoder.
result Graph2Tree model outperforms or matches state-of-the-art models on neural semantic parsing and math word problem tasks.
Study proves Lojasiewicz inequalities for harmonic maps near simple bubble trees.
problem Analyzing harmonic maps near simple bubble trees.
method Proves Lojasiewicz inequalities for harmonic maps close to simple bubble trees.
result Obtains new results on the convergence of harmonic map flow and energy spectrum.
Simple image augmentation boosts deep RL from pixels.
problem Training deep RL models from raw pixel inputs is challenging.
method Applying standard computer vision data augmentation to reinforcement learning.
result Our method significantly improves SAC's performance on DeepMind control suite.
New method embeds phylogenetic trees for clustering, recovering evolutionary relationships.
problem Lack of a meaningful way to embed phylogenetic trees into a vector space.
method Split-weight embedding to fit clustering algorithms to phylogenetic trees.
result Split-weight embedding recovers meaningful evolutionary relationships in simulated and real data.
We present the first tree-based regressor whose convergence rate depends only on the intrinsic dimension of the data, namely its Assouad dimension. The regressor uses the RPtree partitioning procedure, a simple randomized variant of k-d trees.
The paper proposes a new algorithm to select subsets of training data for better accuracy and explainability.
problem Tackles the challenge of balancing accuracy and explainability in pattern recognition.
method Identifies multiple subsets with simple local patterns by clustering similar instances.
result The sub-setting algorithm outperformed traditional decision trees by 15% on the international stroke dataset.
Batch augmentation improves deep learning training by reducing batch size requirements.
problem Training deep neural networks with large batches can lead to overfitting.
method Replicate samples within a batch with different data augmentations.
result Batch augmentation reduces the number of necessary SGD updates for achieving the same accuracy.
Study evaluates Tree-Ring Watermarking in rectified flow-based models, revealing detection and separability limitations.
problem Detecting and separating Tree-Ring Watermarks in rectified flow-based models.
method Extensive experimentation comparing SD 2.1 and FLUX.1-dev models with various text guidance configurations and augmentation attacks.
result Inversion limitations affect watermark recovery and statistical separation.
A new method improves model trees for higher accuracy and transparency.
problem Combining transparency and high accuracy in machine learning models.
method Gradient-based split criterion for model trees.
result Significantly higher predictive power with simpler models.
This study benchmarks data augmentation schemes to improve CNN performance.
problem Lack of training data for deep learning models.
method Various geometric and photometric data augmentation schemes evaluated on a CNN.
result Cropping in geometric augmentation significantly improves CNN task performance.
Algorithm removes leaves to find root in uniform trees.
problem Finding the root in large uniform attachment trees.
method Leaf-stripping algorithm recursively removes leaves.
result Set of remaining vertices contains the root with high probability.
Determinants of theta curves and symmetric graphs are studied.
problem Understanding the determinants of theta curves and symmetric graphs.
method Combinatorial approach using Kirchhoff's Matrix Tree Theorem and spanning tree enumeration.
result The determinant of a simple theta curve is the product of the determinants of its constituent knots.
A new method for dataset augmentation in feature space.
problem Lack of domain-specific transformations and limited re-use in dataset augmentation.
method Apply simple transformations in a learned feature space of context vectors.
result Effective for both static and sequential data.
RAD enhances RL algorithms with data augmentations.
problem Challenges in RL learning from visual observations.
method RAD is a simple plug-and-play module for RL algorithms.
result RAD improves data-efficiency and final performance.
ARL uses MCTS to explore rewards efficiently, outperforming standard RL methods.
problem Challenging exploration in ARL due to limited reward feedback.
method ARL algorithm using MCTS, based on Bayes-Adaptive MDPs.
result Near-optimal performance on small problems, superior to Q-learners on larger ones.
The paper studies actions on Bass-Serre trees and identifies new C∗-simple groups.
problem Investigating actions of fundamental groups on Bass-Serre trees and their C∗-algebraic properties. method Analyzing boundary actions of fundamental groups of graphs of groups on their Bass-Serre trees.
result Identification of new families of C∗-simple groups, including tubular groups and certain graphs of groups.