Dropout is a simple but efficient regularization technique for achieving better generalization of deep neural networks (DNNs); hence it is widely used in tasks based on DNNs. During training, dropout randomly discards a portion of the neurons to avoid overfitting. This paper presents an enhanced dropout technique, whic…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “duplicated samples”
The paper tackles uniform sampling from databases with duplicates.
problem Sampling uniformly from entities with duplicate records.
method Two-stage process: frequency estimation followed by rejection sampling.
result Efficient sampling algorithms under various data properties.
Don't Throw Away Your Beams: Improving Consistency-based Uncertainties in LLMs via Beam Searchstat.ML
Beam search improves UQ in LLMs by reducing duplicates and variance.
problem Peaked distributions in multinomial sampling lead to duplicates and high variance in uncertainty estimates.
method Employ beam search to generate candidates for consistency-based UQ, providing a theoretical lower bound and empirical evaluation.
result Beam search achieves smaller error than multinomial sampling, leading to state-of-the-art UQ performance.
MNIST and Fashion MNIST are extremely popular for testing in the machine learning space. Fashion MNIST improves on MNIST by introducing a harder problem, increasing the diversity of testing sets, and more accurately representing a modern computer vision task. In order to increase the data quality of FashionMNIST, this …
Bayesian approach for multifile record linkage and duplicate detection.
problem Challenges in merging overlapping datafiles with duplicates.
method Bayesian approach with novel partition representation and loss functions.
result Proposes a flexible prior for partitions and uncertain unresolved portions.
Postprocessing reduces Bayesian optimization steps for global optima.
problem Slow convergence in Bayesian optimization for high-dimensional problems.
method Prohibits duplicated samples in the dataset postprocessing method.
result Significantly reduces the number of sequential steps to find the global optimum.
Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while l…
Heat-Kernel Entropy Profiles and Geometric Effective Sample Size for Weighted Measures on Manifoldsstat.ML
New summary measures reveal geometric structure in weighted measures on manifolds.
problem Lack of geometric information in standard weight-only summaries.
method Heat-kernel entropy profiles, tracking nonuniformity across scales.
result Geometric effective sample size discounts nearby or duplicate particles.
We identify a duplicate pair in the well-known Callahan-Hildebrand-Weeks census of cusped finite-volume hyperbolic 3-manifolds. Specifically, the six-tetrahedron non-orientable manifolds x101 and x103 are homeomorphic.
Tricks adversarial attacks to target specific classes, improving classifier accuracy.
problem Recent adversarial defense approaches have failed to protect classifiers from untargeted attacks.
method Target Training defense tricks untargeted attacks into targeted attacks on designated classes, then derives the real class.
result 86.2% accuracy for CW-L2 (confidence=0) in CIFAR10, outperforming unsecured classifiers.
A Python package solves source duplication in single channel LVMs using spectral regularisation.
problem Source duplication in LVMs hampers their practical use in single channel applications.
method Spectral regularisation term added to address source duplication issue.
result Spectral regularisation framework enables easier investigation and utilisation of LVMs.
We are able to derive the equations of motion for forced mechanical systems in a purely variational setting, both in the context of Lagrangian or Hamiltonian mechanics, by duplicating the variables of the system as introduced by Galley [2013], Galley, Tsang, and Stein [2014]. We show that this construction is useful to…
This paper identifies duplicate questions on Quora using machine and deep learning models.
problem Detecting semantically identical questions on Quora to improve user experience.
method Applied machine learning and deep learning techniques on Quora's dataset.
result Xgboost model with character level term frequency and inverse term frequency achieved 85.82% accuracy.
this is a duplicate submission(original is arXiv:1612.02141). Hence want to withdraw it
Efficiently samples sequences without replacement for machine learning models.
problem Generating diverse outputs from sequential models without duplicates.
method Incremental sampling procedure for randomized programs, including neural models.
result Efficacy and flexibility of incremental sampling for large output spaces.
New estimator reduces variance in discrete random variables.
problem Estimating gradients for discrete random variables with reduced variance.
method Sampling without replacement and Rao-Blackwellization.
result Our estimator is the most consistent gradient estimator across different entropy settings.
CARMS improves gradient estimation for categorical variables.
problem Accurately backpropagating gradients through categorical variables.
method CARMS combines REINFORCE with antithetic sampling to create unbiased gradient estimators.
result CARMS outperforms competing methods on various tasks.
We introduce a new sampling method for large language models that balances diversity and parallelism.
problem Balancing diversity and parallelism in decoding for large language models.
method Arithmetic sampling framework compatible with various sampling variations.
result Improves estimation of expected BLEU score reward and reduces the gap with beam search.
Sampling with replacement occurs in many settings in machine learning, notably in the bagging ensemble technique and the .632+ validation scheme. The number of unique original items in a bootstrap sample can have an important role in the behaviour of prediction models learned on it. Indeed, there are uncontrived exampl…
The papers math.QA/0403527 and math.QA/0409414 v.1 are now merged together. The final version is available at math.QA/0409414 v.2. To avoid duplication of papers, math.QA/0403527 is now removed.
Robustness Analysis of Hottopixx, a Linear Programming Model for Factoring Nonnegative Matricesstat.ML
Although nonnegative matrix factorization (NMF) is NP-hard in general, it has been shown very recently that it is tractable under the assumption that the input nonnegative data matrix is close to being separable (separability requires that all columns of the input matrix belongs to the cone spanned by a small subset of…
The long standing classification problem in the theory of Heegaard splittings of 3-manifolds is to exhibit for each closed 3-manifold a complete list, without duplication, of all its irreducible Heegaard surfaces, up to isotopy. We solve this problem for non Haken hyperbolic 3-manifolds.
RGRR allocates between QQQ and DIA based on relative states, improving Sharpe and CAGR.
problem Optimizing ETF allocation between QQQ and DIA for better risk-adjusted returns.
method Screened relative and macro states, globally screened interactions, fixed position mapping, walk-forward validation.
result RGRR improves Sharpe and CAGR compared to 100% QQQ and 50/50 QQQ-DIA allocations.
Data de-duplication is the task of detecting multiple records that correspond to the same real-world entity in a database. In this work, we view de-duplication as a clustering problem where the goal is to put records corresponding to the same physical entity in the same cluster and putting records corresponding to diff…
Cost-effective feature selection improves network model choice.
problem Selecting informative features from noisy candidates in network models.
method Adapted feature selection methods to account for feature costs and used pilot simulations.
result Reduced computational cost by two orders of magnitude without sacrificing model accuracy.
We develop a new method for proving regularity for small energy stationary solutions of coupled gauge field equations. Our results duplicate those of Tian--Tao [7] for the pure Yang Mills equations, but our proof is simpler, and obtains bounded curvature without the use of Coulomb gauges. It relies instead on the Weitz…
A simple model of price formationcond-mat.stat-mech
A simple Ising spin model which can describe the mechanism of price formation in financial markets is proposed. In contrast to other agent-based models, the influence does not flow inward from the surrounding neighbors to the center site, but spreads outward from the center to the neighbors. The model thus describes th…
EnsembleSVM is a free software package containing efficient routines to perform ensemble learning with support vector machine (SVM) base models. It currently offers ensemble methods based on binary SVM models. Our implementation avoids duplicate storage and evaluation of support vectors which are shared between constit…
Interacting particle methods are increasingly used to sample from complex and high-dimensional distributions. These stochastic particle integration techniques can be interpreted as an universal acceptance-rejection sequential particle sampler equipped with adaptive and interacting recycling mechanisms. Practically, the…
RW-based learning is vulnerable to the Pac-Man attack, which eliminates active RWs.
problem Vulnerability of RW-based learning to malicious behavior.
method Proposed the Average Crossing (AC) algorithm to prevent RW extinction.
result RW-based stochastic gradient descent remains convergent under AC, even in the presence of Pac-Man.
FairWASP optimizes training data to reduce disparities across subgroups.
problem Reducing disparities in model outputs across different subgroups in machine learning.
method A novel pre-processing approach that minimizes Wasserstein distance to the original dataset while satisfying demographic parity.
result Integer weights are optimal, allowing FairWASP to be understood as duplicating or eliminating samples.
We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with t…
CMTS: Conditional Multiple Trajectory Synthesizer for Generating Safety-critical Driving Scenarioscs.LG
Naturalistic driving trajectories are crucial for the performance of autonomous driving algorithms. However, most of the data is collected in safe scenarios leading to the duplication of trajectories which are easy to be handled by currently developed algorithms. When considering safety, testing algorithms in near-miss…
New model shows hierarchical proof structure helps theorem provers.
problem How to efficiently learn proofs from teacher traces.
method Model proof search as MDP, analyze imitation learning from traces.
result Hierarchical proof structure leads to more efficient learning.
We obtain an analog of the compression of angles theorem in symmetric spaces for Bruhat--Tits buildings of the type . More precisely, consider a -adic linear space and the set of all lattices in . The complex distance in is a complete system of invariants of a pair of points of u…
Boomerang generates nonidentical images similar to input on image manifolds.
problem Generating nonidentical images similar to input on image manifolds.
method Adding noise to input image, moving closer to latent space, and mapping back through partial reverse diffusion.
result Boomerang generates nonidentical images similar to input on image manifolds.
In this work we present a complete (no misses, no duplicates) census for closed, connected, orientable and prime 3-manifolds induced by plane graphs with a bipartition of its edge set (blinks) up to edges. Blinks form a universal encoding for such manifolds. In fact, each such a manifold is a subtle class of blin…
A new deep model generates molecules by fragments, improving validity and uniqueness.
problem Generating valid and unique molecules using deep learning.
method Develops a language model for molecular fragments, using frequency-based masking.
result Significantly outperforms other language model-based competitors in molecule generation.
The study proves limitations on isospectral hyperbolic surfaces with discrete length spectra.
problem Characterizing isospectral hyperbolic surfaces with discrete length spectra.
method Utilizing Sunada's method and topological self-duplicating ends, the study explores isospectral families and their cardinality.
result Finite groups can be realized as full isometry groups of hyperbolic structures with discrete spectrum on surfaces with self-duplicating ends.
Question semantic similarity (Q2Q) is a challenging task that is very useful in many NLP applications, such as detecting duplicate questions and question answering systems. In this paper, we present the results and findings of the shared task (Semantic Question Similarity in Arabic). The task was organized as part of t…
Entity resolution seeks to merge databases as to remove duplicate entries where unique identifiers are typically unknown. We review modern blocking approaches for entity resolution, focusing on those based upon locality sensitive hashing (LSH). First, we introduce -means locality sensitive hashing (KLSH), which is b…
We have analyzed the risks of possible development of bubbles in the Swiss residential real estate market. The data employed in this work has been collected by comparis.ch, and carefully cleaned from duplicate records through a procedure based on supervised machine learning methods. The study uses the log periodic powe…
Improved defense against data poisoning attacks by aggregating smaller subsets.
problem Mitigating the impact of poisoned data on model robustness.
method Finite Aggregation method that combines duplicates of smaller disjoint subsets for training.
result Consistent improvement in certified robustness bounds, up to 4.77% on GTSRB.
New integral transforms solve multilayer heat equations.
problem Solving multilayer heat equations with moving boundaries.
method Expanding Dirac delta function in eigenfunctions, constructing oscillating integral transforms.
result Semi-analytical solutions for various problems.
EagerPy simplifies writing code for multiple deep learning frameworks.
problem Code duplication and framework lock-in when using different deep learning libraries.
method Integrates multiple frameworks into a single Python framework.
result Automatic compatibility across PyTorch, TensorFlow, JAX, and NumPy.
Large-scale collections of electronic records constitute both an opportunity for the development of more accurate prediction models and a threat for privacy. To limit privacy exposure new privacy-enhancing techniques are emerging such as federated learning which enables large-scale data analysis while avoiding the cent…
Detects AI-synthesized speech using cepstral and bispectral analysis.
problem Validating the authenticity of speech from AI-generated content.
method Integrates cepstral and bispectral analysis for distinguishing human from AI-synthesized speech.
result Higher-order statistics show less correlation for human speech compared to AI-synthesis, and cepstral analysis reveals unique power components.
Record linkage involves merging records in large, noisy databases to remove duplicate entities. It has become an important area because of its widespread occurrence in bibliometrics, public health, official statistics production, political science, and beyond. Traditional linkage methods directly linking records to one…