DDBF improves random forest for imbalanced data.
problem Learning from imbalanced data.
method Incorporates hard example mining into random forest, dynamically removing easy examples.
result DDBF outperforms random forest on multiple datasets.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,181 papers · 148 categories
Trend · papers per month
48 results for “hard example mining”
S2M optimizes mining for diverse data subpopulations.
problem Scalability and uniformity in training sets with many labels and diverse data.
method Doubly-stochastic mining (S2M) computes per-example and minibatch losses on hardest labels/examples.
result S2M ensures good performance across all data subpopulations.
GCBS improves contrastive learning performance efficiently.
problem Efficiently mining hard negatives for contrastive learning.
method Global Contrastive Batch Sampling (GCBS) approximates batch assignment problem.
result GCBS improves state-of-the-art performance in sentence embedding and code-search tasks.
System simplifies feedback from domain experts for iterative rule mining.
problem Difficulty in incorporating domain experts' feedback and evaluating multi-objective models.
method Developed a multi-objective anytime rule mining algorithm based on GRASP-PR.
result Successfully applied the system in an industrial context.
PS-KD distills a model's own knowledge to soften hard targets during training.
problem Improving generalization of deep neural networks by softening hard targets.
method Progressive self-knowledge distillation (PS-KD) that progressively distills a model's own knowledge to soften hard targets.
result PS-KD improves accuracy and provides high quality of confidence estimates in terms of calibration and ordinal ranking.
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …
A popular tool for unsupervised modelling and mining multi-aspect data is tensor decomposition. In an exploratory setting, where and no labels or ground truth are available how can we automatically decide how many components to extract? How can we assess the quality of our results, so that a domain expert can factor th…
ATOM improves robust OOD detection by mining informative auxiliary examples.
problem Robust OOD detection in open-world settings is challenging due to adversarial inputs.
method ATOM combines adversarial training with outlier mining to improve robustness.
result ATOM achieves state-of-the-art performance in OOD detection, reducing FPR by up to 57.99%.
Deep metric learning detects anomalies without labels.
problem Unsupervised anomaly detection for high-dimensional data.
method Deep metric learning with end-to-end optimization, data distillation, hard mining.
result Significant performance gains over state-of-the-art methods.
The paper analyzes how curriculum learning improves machine learning performance.
problem Lack of theoretical analysis for curriculum learning in machine learning.
method Formulated an ideal difficulty score and analyzed its contribution in convex problems.
result The expected convergence rate decreases with the ideal difficulty score.
Data mining enhances a heuristic for the Minimum Latency Problem.
problem Finding optimal solutions for the Minimum Latency Problem efficiently.
method Combining GRASP with data mining to find frequent patterns in high-quality solutions.
result Improved solution quality and reduced computational time compared to existing methods.
This work learns shared word embeddings for acoustic and phonetic sequences.
problem Mapping variable-length acoustic and phonetic sequences to fixed-dimensional vectors.
method Weak supervision and binary classification task to predict word similarity.
result Best model achieves an F1 score of 0.95 for binary classification.
Identifies a sub-matrix with maximal sum in large data matrices.
problem Finding a rectangular sub-matrix with the highest sum of entries.
method Proposes two algorithms: CP-GC and MILP, leveraging problem characteristics.
result CPGC approach tends to be the fastest to produce a good solution.
Hard Diagrams of the Unknotmath.GT
Three hard diagrams of the unknot require extra crossings to simplify.
problem Finding diagrams of the unknot that require many crossings to simplify.
method Applying previously proposed methods to construct diagrams and using computational resources to prove their hardness.
result Three hard diagrams of the unknot require at least three extra crossings.
Prototypical examples that best summarizes and compactly represents an underlying complex data distribution communicate meaningful insights to humans in domains where simple explanations are hard to extract. In this paper we present algorithms with strong theoretical guarantees to mine these data sets and select protot…
This paper shows how optimizing with hard negative examples improves image retrieval.
problem Training with hard negative examples leads to poor training behavior.
method Characterize the space of triplets, derive why hard negatives fail, and offer a fix to the loss function.
result Optimizing with hard negative examples leads to more generalizable features and better image retrieval.
New Ising models improve consensus clustering on specialized hardware.
problem Consensus clustering optimization problems.
method Formulated consensus clustering as Ising models and evaluated on specialized hardware.
result Our Ising models outperform existing techniques on consensus clustering.
Detecting adversarial examples is as hard as classifying them.
problem The difficulty of detecting adversarial examples in machine learning models.
method Proved a general hardness reduction between detection and classification of adversarial examples.
result The hardness reduction implies that detecting adversarial examples is computationally infeasible.
Automatically mined rules from dependency parsing help neural models learn from less labeled data.
problem Lack of labeled data for aspect and opinion term extraction.
method Automatically mined rules from dependency parsing, applied to auxiliary data, combined with human-annotated data.
result Neural models achieve better performance than state-of-the-art with mined rules and auxiliary data.
This work connects hardness of approximation and learning.
problem Hardness of approximation and learnability in machine learning.
method Shows a single hardness property implying both approximation and learning hardness.
result Obtains new results on hardness of approximation and learnability of specific functions.
Confidence intervals improve evaluation of binary prediction rules in data mining.
problem Uncertainty in performance measures estimation from finite datasets.
method Asymptotic normal approximations for confidence intervals, with a blurring correction.
result Improved finite sample coverage probabilities and general performance measures inference.
Paper presents a framework to automatically discover constraints from data.
problem Discovering constraints from data for structured output prediction.
method Formulates structured output prediction as ILP, mines constraints by estimating polytopes of feasible set.
result Successfully identifies feasible sets and constraints for various tasks.
The Hard Lefschetz Theorem extends to certain Kähler Lie Algebroids with ellipticity.
problem Extending the Hard Lefschetz Theorem to Kähler Lie Algebroids.
method Analyzing a specific class of Kähler Lie Algebroids with ellipticity requirements.
result A class of Kähler Lie Algebroids satisfy the Hard Lefschetz Theorem with ellipticity.
We describe a method for generating minimal hard prime surface-link diagrams. We extend the known examples of minimal hard prime classical unknot and unlink diagrams up to three components and generate figures of all minimal hard prime surface-unknot and surface-unlink diagrams with prime base surface components up to …
ELF improves long-tailed classification by focusing on hard examples.
problem Overfitting to majority classes in long-tailed data distributions.
method EARLY-exiting Framework with auxiliary branches.
result Improves accuracy by more than 3 percent on ImageNet LT and iNaturalist'18.
A simple framework improves deep metric learning performance.
problem Imbalanced data pairs in pairwise deep metric learning.
method Formulated a robust loss for balanced pairs over mini-batches, using distributionally robust optimization.
result Empirically outperforms state-of-the-art methods.
Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by introducing a novel metric learning based objective function. This objective fun…
A new model for graph clustering using curvature spaces.
problem Graph clustering from a geometric perspective.
method Introducing a heterogeneous curvature space and a contrastive learning approach.
result CONGREGATE model outperforms state-of-the-art competitors.
Study shows computational hardness can improve adversarial robustness in learning.
problem Developing robust machine learning models against adversarial attacks.
method Investigate if computational limitations of attackers can enhance robustness.
result Demonstrated a learning task where computational robustness outperforms information-theoretic robustness.
This paper proposes a communication-efficient distributed algorithm for high-dimensional data mining.
problem Reducing communication time and rounds in distributed data mining.
method Straggler-agnostic and bandwidth-efficient distributed primal-dual algorithm.
result Guaranteed linear convergence rate for convex problems.
Paper shows examples of almost Kähler manifolds satisfying Hard Lefschetz but not Betti-Hodge equality.
problem Understanding the Hard Lefschetz condition in almost Kähler manifolds.
method Examples and counterexamples of compact almost Kähler manifolds.
result The Hard Lefschetz condition does not imply the equality between Betti and Hodge numbers in almost Kähler manifolds.
Karate Club simplifies graph mining for unsupervised learning.
problem Efficient unsupervised learning on graphs.
method API-oriented Python framework combining 30+ algorithms.
result Karate Club outperforms in learning performance and speed.
New sampling method improves search efficiency in machine learning.
problem Efficiently sampling effective solutions from large search spaces.
method Developed a parameterized family of coverage-based designs and algorithms for effective synthesis.
result Consistently outperforms existing exploratory sampling methods in sample mining and hyper-parameter optimization.
Proposes a novel method for generating hard negatives near time series data boundaries.
problem Challenges in generating effective negative samples for time series anomaly detection.
method Reconstruction-driven boundary negative generation framework using reinforcement learning.
result Improves anomaly representation learning and achieves competitive detection performance.
Randomization helps verify if data mining results are due to inherent patterns.
problem Verify if data mining results are due to inherent patterns or coincidental findings.
method Metropolis sampling based on local swaps to randomize data while preserving discovered patterns.
result Randomized data often reveals that clustering results imply frequent pattern discovery.
AVH scores measure sample hardness, improving model calibration.
problem CNNs' poor calibration and overconfidence issues.
method AVH score based on normalized angular distance between feature embeddings and target classifiers.
result AVH scores correlate with human visual hardness and improve model calibration.
Mind the Gap in the Mining Gameq-fin.GN
Game-theoretic analysis of mining gaps in blockchain systems.
problem Strategic mining behavior and its impact on blockchain stability.
method Game-theoretic model and Nash equilibrium analysis.
result Mining gaps can destabilize blockchain systems, especially with decreasing block rewards.
Study categorizes knots and links as rigid or shaky based on Reidemeister moves.
problem Classifying knots and links as rigid or shaky based on adaptability to Reidemeister moves.
method Categorization of hard diagrams as rigid or shaky, investigation of rigid and shaky hard diagrams for specific knots and links.
result Every link has a rigid hard diagram, and there is an upper limit for the number of crossings in such diagrams.
Efficient method for generating adversarial examples with limited query budget.
problem Developing black-box adversarial attacks with limited information.
method Bayesian Optimization in a structured low-dimensional subspace.
result Significantly higher attack success rate with fewer queries.
This paper examines feature selection for extracting user intentions from Twitter.
problem Extracting user intentions from informal, misspelled tweets.
method Developed a dataset from Twitter feeds, used two feature selection techniques (Information Gain and hybrid forward selection), and applied four classification algorithms.
result The hybrid feature selection approach outperformed the Information Gain method.
The paper proves a generalized Lefschetz duality for a specific type of manifold.
problem Proving the hard Lefschetz duality for a new class of manifolds.
method Generalizing Kähler identities to prove the duality for locally conformally almost Kähler manifolds.
result The hard Lefschetz duality is established for locally conformally almost Kähler manifolds.
Alpha-GPT mines new trading signals with human-AI interaction.
problem Mining new alphas for effective trading signals.
method Human-AI interaction and prompt engineering algorithmic framework.
result Demonstrates Alpha-GPT's effectiveness in generating creative, insightful, and effective alphas.
The paper explores how mining costs, rewards, and blockchain security are interconnected.
problem Understanding the interdependencies between mining costs, mining rewards, and blockchain security.
method Theoretical derivation and empirical analysis using daily crypto market data and autoregressive distributed lag approach.
result Cryptocurrency price and mining rewards are intrinsically linked to blockchain security outcomes.
Nonnegative matrix factorization (NMF) has become a widely used tool for the analysis of high-dimensional data as it automatically extracts sparse and meaningful features from a set of nonnegative data vectors. We first illustrate this property of NMF on three applications, in image processing, text mining and hyperspe…
Paper introduces impact curves for evaluating binarized regression models with varying costs.
problem Evaluating binarized regression models with varying costs and instance-specific utility.
method Proposes impact curves to optimize binary decisions across different utilities.
result Impact curves identify conditions where one model is favored over another and quantify model improvement.
Data preprocessing improves data quality for robust data mining.
problem Noisy and incomplete data hinders data mining models.
method Overview of data cleaning, transformation, and preprocessing methods.
result Preprocessing significantly affects data mining model performance.
New method expands seed genes to functionally related clusters.
problem Discovering functionally related genes lacking GO terms.
method Semi-supervised learning with positive and unlabeled examples.
result LPU approaches significantly outperform existing methods.
This paper categorizes and analyzes existing outlying aspect mining methods.
problem Finding unique features in data objects that differ from others.
method Grouping and analyzing existing outlying aspect mining approaches in three categories.
result Comparison of strengths, weaknesses, and time complexities of different techniques.