CN-SBM clusters cancer samples and regions based on copy number variants.
problem Clonal evolution in cancer monitored by noisy copy number variants.
method Probabilistic framework using bipartite categorical block model.
result Improved model fit and clinically relevant subtypes identified.
SmoothOut improves deep learning by smoothing out sharp minima, enhancing generalization.
problem Sharp minima in deep neural networks lead to poor generalization.
method SmoothOut framework that perturbs multiple copies of the DNN by noise injection and averages them, improving generalization.
result SmoothOut eliminates sharp minima and improves generalization in both small-batch and large-batch training.
Develops a framework to copy any machine learning classifier without prior knowledge.
problem Copying machine learning classifiers without access to their parameters or training data.
method Theory and framework development, synthetic set generation, loss identification, and evaluation metrics.
result Copies can enhance existing solutions and add new features.
Advances in asynchronous optimization methods for machine learning.
problem Efficiently solving large-scale optimization problems in machine learning.
method Asynchronous parallel and distributed optimization methods, accounting for information delays.
result Degree of asynchrony impacts convergence rates in stochastic optimization methods.
Decomposes information into copying and transformation modes.
problem Lack of distinction between copying and transformation in information measures.
method Derives a decomposition of mutual information into copying and transformation components.
result Copy information can be interpreted as minimal physical copying work.
Study on how deterministic dependencies affect information synergy and redundancy.
problem Understanding how deterministic dependencies impact information synergy and redundancy.
method Systematic analysis of deterministic dependencies on information decomposition.
result Identifies how negative terms can originate from deterministic dependencies and discusses implications for neural coding.
This paper introduces DPI, a new metric to assess data-copying risk in tabular data.
problem Measuring privacy risk of data-copying in tabular generative models.
method Proposes Data Plagiarism Index (DPI) for evaluating data-copying risk.
result DPI identifies data-copying threats to tabular data models, highlighting privacy and fairness issues.
New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.
problem Editing documents or source code using seq2seq models with explicit token copying.
method Extended seq2seq model capable of copying entire input spans to output in one step, new training and inference methods.
result New model consistently outperforms simpler baselines in editing tasks of natural language and source code.
The paper proposes sampling strategies for classifier copies.
problem Generating unlabelled points to explore decision behavior.
method Two sampling strategies compared with two standard methods.
result Validation in six problems and comparison of performance and cost.
Paper analyzes gradient descent with noisy data copies for linear regression, showing regularization and acceleration effects.
problem Improving generalization in machine learning through data augmentation with noise.
method Gradient descent with on-line noisy copies for linear regression analysis.
result Training with on-line noisy copies is equivalent to ridge regularization with a specific regularization parameter.
Smooth lens spaces embed in complex projective planes but not in finite copies.
problem Embedding lens spaces in complex projective planes.
method Analyzes smooth and locally flat embeddings of lens spaces in complex projective planes.
result No finite number of copies of complex projective plane can embed every lens space smoothly.
New test detects when generative models memorize training data.
problem Detecting when generative models overfit by memorizing training data.
method A non-parametric three-sample test using training set, target distribution, and model-generated samples.
result The test effectively detects data-copying in various models and datasets.
Shapes can roll downhill following any curve, but often return to initial orientation after crossing multiple copies.
problem How to design shapes that roll downhill along a given curve and its translations.
method Analyzing the geometric properties and motion of shapes on inclined planes.
result Most curves allow shapes to roll downhill following them and their translations, but some require crossing multiple copies.
Paper proposes a neural network for generating better questions from text.
problem Automatic generation of relevant questions from sentences and paragraphs.
method Adaptive copying recurrent neural network model with a copying mechanism added to a bidirectional LSTM architecture.
result The model outperforms state-of-the-art methods in question generation metrics.
New system resists meme coin copy trading bots.
problem Manipulative bots exploit copy trading in illiquid meme coins.
method Multi-agent architecture with LLM and CoT reasoning.
result System outperforms other methods in prediction and economic performance.
GMC benchmark isolates retrieval in Transformers, revealing max-margin alignment.
problem Understanding how Transformers develop match-and-copy behavior on natural data.
method Introducing Gaussian Match-and-Copy (GMC) as a minimalist benchmark.
result Gradient descent drives parameters to diverge while aligning with max-margin separator.
Bayesian theory explains abrupt emergence of copy subcircuit in attention.
problem Understanding the abrupt emergence of the copy subcircuit in attention during training.
method Deriving a closed-form posterior over the attention matrix and reducing it to a low-dimensional order parameter space.
result Derive a phase transition in the amount of training data.
Under-parameterized networks can either copy or average teacher weights, leading to universal optimal solutions.
problem Approximating a teacher network with an under-parameterized student network.
method Analyzing shallow neural networks with erf activation function and unitary teacher weights, proving copy-average configurations are critical points and finding the optimal solution.
result The optimal solution for under-parameterized networks has a universal structure, whether copying or averaging teacher neurons.
A condition for the existence of false gauge field copies in terms of the Lefschetz number of a certain differential operator is presented.
P-value hacking can produce misleadingly low p-values, skewing meta-analysis results.
problem Misleading p-values in meta-analysis due to p-value hacking.
method Deriving the meta-distribution for p-values and analyzing the power of tests.
result Minimum p-values can be significantly lower than the true p-value, skewing results.
A new method improves convergence of gradient-based optimizers without manual tuning.
problem Improving the convergence rate of gradient-based optimizers.
method Dynamic learning rate adaptation using hypergradient descent.
result Significantly reduces the need for manual tuning of initial learning rates.
The paper introduces a new method to improve model generalization by routing model copies through permutations.
problem Improving model generalization in machine learning.
method The method replicates a model \(M\) times and rewire the contexts in which local learning messages are computed using permutations.
result The method improves generalization by structured message sharing rather than coupling parameters.
Bayesian GCNN uses node copying for graph inference.
problem Uncertainty in graph structure.
method Generative model based on node copying within BGCN framework.
result Proposed algorithm outperforms state-of-the-art in node classification tasks.
A simple patch copying method reduces black-box adversarial attack queries by 81%.
problem The effectiveness of black-box adversarial attacks depends on the initialization method.
method Copying small patches from other images as initialization points.
result Reduces the number of queries required for a state-of-the-art Boundary Attack by 81%
New manifold copies found through knot iterations.
problem Finding infinitely many exotic smooth structures on a 4-manifold.
method Using a specific knot and its iterates to attach 2-handles to a fixed compact manifold.
result Infinitely many absolutely exotic copies of a 4-manifold are constructed.
We show that the maximal orbit dimension of a simultaneous Lie group action on n copies of a manifold does not pseudo-stabilize when n increases. We also show that if a Lie group action is (locally) effective on subsets of a manifold, then the induced Cartesian action is locally free on an open subset of a sufficiently…
A scalable algorithm for sampling and fine-tuning models using Tilt Matching.
problem Efficient sampling and fine-tuning of generative models.
method Tilt Matching, arising from a dynamical equation, minimizes variance and inherits regularity from stochastic interpolants.
result Empirically verified to be efficient and highly scalable, providing state-of-the-art results.
A caching mechanism improves sequence to logical form generation accuracy.
problem Generating logical forms from natural language sequences.
method Proposes a caching mechanism to increase output probability of source input tokens and weigh them based on context.
result Improves sequence/token-level accuracy on sequence to logical form tasks.
A free action of the direct product of two copies of the symmetric group on 3 elements on the cartesian product of two copies of the 3-sphere is constructed. This nonlinear action is constructed using surgery. The action provides a counterexample to a conjecture of Lewis made in 1968.
Optimizes web page freshness with limited crawling frequencies.
problem Maximize local cache freshness given crawling frequency constraints.
method Three novel online estimation schemes for page change rates.
result Convergent algorithms for estimating page change rates.
A fibration of Rn by oriented copies of Rp is called skew if no two fibers intersect nor contain parallel directions. Conditions on p and n for the existence of such a fibration were given by Ovsienko and Tabachnikov. A classification of smooth fibrations of R3 by skew oriente…
For a closed 4-manifold X and closed 3-manifold M we investigate the smallest integer n (perhaps infinity) such that M embeds in the connected sum of n copies of X. It is proven that any lens space (or homology lens space) embeds topologically locally flatly in a connected sum of 8 copies of the complex projective plan…
We construct branched double coverings by certain direct products of manifolds for connected sums of copies of sphere bundles over the 2-sphere. As an application we answer a question of Kotschick and Loeh up to dimension five. More precisely, we show that: (1) every simply connected, closed four-manifold admits a bran…
New algorithms for fair item allocation with limited copies.
problem Fair division of numerous items with few copies.
method Modeling as a contextual bandit problem with sub-linear regret guarantees.
result Proposed algorithms achieve sub-linear regret in fair item allocation.
Learning machines can mimic the dynamics of black systems without knowing their equations.
problem Simulating black systems without knowing their equations of motion.
method Train a learning machine with input-output responses or time series of a black system.
result Learning machines can mimic the dynamics of various black systems and their evolution history.
Proves stability of cone-volume measure with nearly constant density.
problem Stability of cone-volume measure with near constant density.
method Proves stability of cone-volume measure with near constant density.
result Homothetic copy of the body is close to the unit ball in the L2-distance. We discuss the relationship between the m-th homotopy group of the one-point union of r copies of the two-dimensional sphere and the m-th homotopy group of the one-point union of r+1 copies of the Thom space of the oriented two-dimensional universal vector bundle. Using a suitably choosen isomorphism between them a for…
Proves conditions for odd pretzel knots to be doubly slice.
problem Identifying conditions for odd pretzel knots to be doubly slice.
method Analyzes knots with specific twist parameters and odd integers.
result Identifies all doubly slice odd pretzel knots.
Characterizes a specific type of Courant algebroid with a Calabi-Yau structure.
problem Understanding specific types of Courant algebroids with Calabi-Yau structures.
method Explains how a homotopy BV algebra with certain properties characterizes these algebroids.
result A Courant algebroid with a Calabi-Yau structure is a homotopy BV algebra with specific properties.
End-to-end character-level model for text generation without delexicalization.
problem Generating text without delexicalization and tokenization.
method Character-level sequence-to-sequence model with attention mechanism, copy mechanism, and transfer learning.
result Competitive performance in text generation metrics.
Special shadow-complexity equals k+1 for k copies of S1×S3.
problem Calculating the special shadow-complexity of a specific 4-manifold.
method Defined by Costantino using Turaev's shadows, proved for connected sums of S1×S3.
result The special shadow-complexity of k copies of S1×S3 is k+1.
CORE optimizes molecules by copying or generating substructures, improving accuracy.
problem Inaccurate substructure prediction in molecule optimization.
method Copy & Refine (CORE) strategy combining scaffolding tree generation and adversarial training.
result Significant improvement in various molecule optimization metrics.
9 generators found for 3-torus skein space.
problem Identifying generators for the skein space of the 3-torus.
method Analyzing the first homology group and constructing specific knots and links.
result The skein space of the 3-torus is generated by 9 specific elements.
A new model for graph sampling that preserves structure without explicit targeting.
problem Graphs are often not fully representative of true relationships, leading to biased machine learning models.
method Node copying model: randomly replaces each node's neighbors with those of a randomly sampled similar node.
result The model achieves higher accuracy in node classification and mitigates adversarial attacks.
CACTI improves tabular data imputation by leveraging missingness patterns and contextual information.
problem Tabular data imputation with improved accuracy and robustness.
method Masked autoencoding approach with median truncated copy masking and contextual information.
result Average R2 gain of 7.8% over the next best method across various datasets and missingness conditions. Copycat CNN learns from random data to mimic target models.
problem Protecting state-of-the-art CNNs from copying.
method Querying target CNN with random non-labeled data to create a fake dataset, then training a copycat network.
result Copycat CNNs can achieve similar performance to target models, even from non-problem domain data.
Zero-Copy Architecture Detects Cross-Company Financial Signals Instantly.
problem Financial models miss cross-company disruptions due to static data.
method Heterogeneous Rust-Python streaming architecture that maps cross-company attention as a continuous-time graph.
result Zero-copy parsing and inference process delivers real-time cross-company signal detection.
We consider canonical symplectic structure on the moduli space of flat ${\g}$-connections on a Riemann surface of genus g with n marked points. For ${\g}$ being a semisimple Lie algebra we obtain an explicit efficient formula for this symplectic form and prove that it may be represented as a sum of n copies of Ki…