A new statistical table summarizes recent longitudinal athlete history.
problem Storing and analyzing longitudinal athlete data efficiently.
method Estimates a Latent Memory Table using a memory operator that maps masked windows to states.
result The Latent Memory Table achieves high quality scores and better wellness target predictions.
A new method reduces embedding size for efficient recommendation systems.
problem Memory bottleneck in embedding tables for diverse categorical features.
method Complementary partitions to produce unique embeddings without explicit definition.
result Our approach reduces embedding size and maintains similar accuracy.
BiQGEMM efficiently multiplies quantized DNN weights using lookup tables.
problem Efficiently multiplying quantized DNN weights on CPUs/GPUs with limited memory.
method BiQGEMM pre-computes and stores redundant intermediate results in lookup tables.
result BiQGEMM achieves lower overall computations and higher performance.
RIn-Close_CVC2 improves biclustering efficiency by reducing memory usage.
problem Mining maximal biclusters in numerical datasets efficiently and without redundancy.
method Proposes RIn-Close_CVC2, a new version of RIn-Close_CVC that eliminates redundant biclusters without a symbol table.
result RIn-Close_CVC2 reduces memory usage and improves runtime compared to RIn-Close_CVC.
Distills neural networks to save memory without changing hyperparameters.
problem Memory constraints in deploying modern neural networks.
method Structural model distillation using attention transfer.
result Significant memory savings with minimal accuracy loss.
A method for reducing neural network size using look-up tables.
problem Reducing memory and computational footprint of deep neural networks.
method Iteratively learns value dictionaries and assignment matrices for network weights.
result General framework for network reduction that can handle various reduction problems.
Paper introduces LUT-Q for efficient neural network quantization.
problem Reducing memory and computational requirements for deep neural networks.
method LUT-Q method learns a dictionary to assign weights to values, allowing for various constraints.
result LUT-Q consistently achieves better performance than other methods with the same quantization bitwidth.
TableNet uses LUTs to create multiplier-less neural networks for faster inferencing.
problem Reducing the computational complexity and power consumption of neural networks during inference.
method Replacing matrix multiply and add operations with LUTs and additions, resulting in a completely multiplier-less implementation.
result Similar performance can be achieved with a comparable memory footprint as a full precision deep neural network, but without multipliers.
Develops a new framework for drawdown risk beyond Gaussian assumptions.
problem Understanding drawdowns in systematic trading strategies.
method Monte-Carlo simulation, non-Gaussian extensions, fractional Brownian motion.
result Drawdowns and related measures vary differently under non-Gaussian assumptions.
SDN optimizes flow entries to reduce control plane overhead.
problem Efficiently manage flow entries in SDN switches with limited TCAM capacity.
method Proposes reinforcement learning algorithms to optimize flow entries.
result Achieves up to 60% reduction in long-term control plane overhead.
Revisit Fenn's table theorem from a differential-topological perspective.
problem Prove zero-existence theorem on a cylinder and horizontal square-table theorem under Fenn's boundary conditions.
method Differential-topological approach.
result Prove horizontal square-table theorem under more general boundary conditions.
A new bootstrapping method reduces key sizes and runtime in FHE.
problem Large plaintext evaluation in FHE increases bootstrapping complexity.
method New polynomial vector representation and monic monomial permutation matrices.
result Polynomial factor improvement in key size and constant factor in runtime.
Efficiently counts data streams in machine learning.
problem Counting queries in machine learning applications.
method Abstracting queries and aggregating as a stream for scalability.
result Significantly outperforms ADtrees and hash tables.
Study detects synthetic tabular data across different tables.
problem Detecting synthetic tabular data in varied tables.
method Four table-agnostic detectors combined with preprocessing schemes.
result Cross-table learning possible with naive preprocessing, but cross-table transfer challenging.
Proves a generalized table theorem for odd Euler characteristic surfaces.
problem Proving a generalized table theorem for surfaces with odd Euler characteristic.
method Using the square peg problem for smooth curves, the result is generalized to real valued functions on Riemannian surfaces with odd Euler characteristic.
result Proves the table conjecture for even functions on the two sphere.
CTSyn generates high-quality synthetic tabular data.
problem Challenges in generating high-quality synthetic tabular data.
method Diffusion-based generative foundation model with autoencoder and conditional latent diffusion.
result CTSyn outperforms existing table synthesizers on standard benchmarks.
This work reduces model size by 86.11% for recommender systems using 4-bit quantization.
problem Large memory consumption in embedding vectors for recommender systems.
method Post-training 4-bit quantization on embedding tables, including row-wise uniform quantization and codebook-based quantization.
result Consistently reduces accuracy degradation while significantly reducing model size.
Upper bounds for surface-links in the Yoshikawa table are estimated.
problem Estimating Kirby-Thompson invariants of surface-links.
method Using tri-plane diagrams and L-, L*-invariants.
result Upper bounds for surface-links in the Yoshikawa table are obtained.
This paper compiles and calculates triple point numbers for surface-links in Yoshikawa's table.
problem Determining the triple point number of surface-links in Yoshikawa's table.
method Using broken sheet diagrams, the paper compiles known triple point numbers and calculates or bounds the remaining ones.
result Compilation and calculation of triple point numbers for surface-links in Yoshikawa's table.
The paper proves geometric properties of square tables and saddle surfaces.
problem The mathematical table problem from a geometric-topological perspective.
method Geometric-topological proofs on cylinder, saddle surfaces, and level sets of Fenn graphs.
result Zero-existence theorem on a cylinder, proving Fenn's square-table theorem under different boundary conditions.
The document provides tables of prehomogeneous and étale modules for reductive algebraic groups.
problem Classifying and tabulating prehomogeneous and étale modules for reductive algebraic groups.
method Classification and tabulation of prehomogeneous and étale modules based on existing work and the author's determination.
result Tables of prehomogeneous and étale modules for reductive algebraic groups with up to two simple factors.
Machine learning speeds up search procedures for sorted tables.
problem Improving the speed of sorted table search procedures.
method Systematic experimental comparison of efficient implementations with learned counterparts.
result Learned data structures can significantly speed up search procedures.
Two ML approaches compare in recognizing tables from historical records.
problem Recognizing rows and columns in hand-written registry books.
method Comparison of Conditional Random Field and Graph Convolutional Network.
result Both ML methods achieve an 89 F1 score for table detection.
Machine learning recreates the periodic table from element properties.
problem Recreating the periodic table using machine learning.
method Unsupervised machine learning with GTM for feature embedding.
result PTG autonomously generates various periodic table layouts.
Generative model improves web table titles.
problem Creating accurate titles for web tables.
method Sequence-to-sequence neural network model with copy and generation mechanisms.
result Model generates titles of comparable quality to human-crowdsourced titles.
Method finds differential equations for integrable billiard tables.
problem Finding differential equations for integrable billiard tables.
method Introducing a method to find differential equations for functions defining tables.
result Illustrated method in three billiard systems.
Billiard trajectories and geodesics are closely related geometrically.
problem Understanding the relationship between billiard trajectories and geodesics on surfaces.
method Establishing mutual approximation results for billiard trajectories and geodesic segments on surfaces.
result For Riemannian billiard tables, there are families of fold-type surfaces such that every sequence of geodesic segments on these surfaces has a subsequence that converges to a billiard trajectory.
BiN normalizes financial time-series for better forecasting.
problem Non-stationarity and multimodality in financial time-series data.
method Bilinear Normalization (BiN) incorporated into TABL networks.
result BiN-TABL outperforms other normalization methods in financial forecasting.
New method improves classification performance in Bayesian networks.
problem Estimating conditional probability tables in Bayesian networks.
method Hierarchical Multinomial-Dirichlet model for joint estimation of conditional distributions.
result Significantly improved classification performance compared to traditional methods.
This note corrects errors in Hatcher and Oertel's table of boundary slopes of Montesinos knots which have projections with 10 or fewer crossings.
Gutkin billiard tables studied in higher dimensions, rigidity proven.
problem Characterizing billiard tables with constant angle invariants.
method New generating function for billiards, rigidity proof.
result In higher dimensions, only spheres have Gutkin billiard tables with constant angle invariants.
Compactness proven for isospectral Birkhoff billiard tables.
problem Proving compactness of isospectral Birkhoff billiard tables.
method Derived a hierarchical structure for integral invariants and used interpolating Hamiltonian.
result Compactness of equivalence classes of marked length isospectral Birkhoff billiard tables.
TableQnA answers web queries about lists and superlatives from HTML tables.
problem Answer web queries about lists and superlatives from HTML tables.
method Extract intent from queries, use structure-aware matching, and train models with automatic data generation.
result Significantly higher precision and coverage for list and superlative queries.
Method combines clustering and matrix completion for missing data in I/O tables.
problem Reconstructing missing entries in World Input-Output (I/O) matrices due to data collection issues.
method Hierarchical clustering and Matrix Completion with LASSO-like nuclear norm penalty.
result The method effectively predicts missing values from previous and similar countries' data.
Proposes φ-table for statistical SHAP explanations in regression models.
problem Lack of clear directional summaries, uncertainty, and fidelity in SHAP feature importance.
method SHAP importance selection, fitting a standardized linear surrogate, reporting coefficients, uncertainty, fidelity, and stability.
result Extends SHAP into a statistical global explanation with direction, uncertainty, fidelity, and stability.
AI can identify simple groups and match algebraic tables, even with limited training.
problem Can AI learn algebraic structures?
method Machine learning techniques (SVM, neural classifiers) applied to finite groups and rings.
result AI can correctly identify simple groups and match algebraic tables for small structures.
An explicit solution found for maximizing/minimizing agreement in a 2x2 table.
problem Maximizing or minimizing agreement between clusterings with given marginals.
method Formal framework for several agreement measures, explicit solution for 2x2 table.
result An explicit solution for the 2x2 case.
FSL-BM improves real-time classification with fuzzy logic and binary meta-features.
problem Real-time classification accuracy, memory consumption, and time complexity.
method FSL-BM integrates fuzzy logic, binary meta-features, Hamming Distance, and Hash function for efficient supervised learning.
result FSL-BM provides faster and more accurate real-time classification compared to existing algorithms.
Robotic table tennis learns efficient policies to return balls at 100Hz.
problem Developing efficient robotic table tennis strategies.
method Model-free reinforcement learning using evolutionary search on CNN-based policies.
result Robots can develop multi-modal styles (forehand and backhand) with 80% return rate.
Open problem: Establishing bounds for Cayley-table completion to discover discrete algorithmic axioms.
problem Discovering discrete algorithmic axioms missing in deep learning.
method Cayley-table completion as a testbed for algorithmic complexity minimization.
result Formal exact recovery bounds for Cayley-table completion.
To study embeddings of tangles in knots, we use quandle cocycle invariants. Computations are carried out for the tables of knots and tangles, to investigate which tangles may or may not embed in knots in the tables.
Improved method for encoding contingency tables reduces mutual information bias.
problem Mutual information bias in measuring label similarity.
method Improved method for encoding contingency tables to reduce information cost.
result Better bound on reduced mutual information in typical use cases.
Enumerated all genus two handlebody-knots with seven crossings.
problem Counting genus two handlebody-knots with specific crossings.
method Extending an existing table of genus two handlebody-knots.
result Enumerated all genus two handlebody-knots with seven crossings.
Paper develops a model for verifying facts in tables without pre-retrieved evidence.
problem Verification of factual claims in structured data, especially in open-domain settings.
method Joint reranking-and-verification model that fuses evidence documents.
result Model achieves comparable performance to closed-domain state-of-the-art on TabFact dataset.
Study on crossing numbers of random two-bridge knots.
problem Understanding the distribution of crossing numbers in random two-bridge knots.
method Used billiard table diagrams to model random knots and derived a closed formula for their crossing numbers.
result Closed formula for the distribution of crossing numbers and exponential decay of knot appearance probability.
Taxicab correspondence analysis visualizes sparse text data sets.
problem Visualization of extremely sparse contingency tables.
method Robust variant of correspondence analysis for sparse data.
result Visualized an 8265-dimensional textual data set.
Characterizes how the shape of a polygon affects billiard dynamics.
problem Understanding how the shape of a billiard table influences its dynamics.
method New theorem linking Liouville current support to flat cone metrics.
result Only right-angled tables with affine differences have identical bounce spectra.
The paper proposes a method to learn Bayesian networks with low rank conditional probability tables.
problem Learning the structure of Bayesian networks efficiently.
method Introduces low rankness for conditional probability tables, connects to Fourier transformation, and proposes a polynomial time algorithm.
result Correctly recovers the true directed structure of a low rank Bayesian network with few queries and polynomial samples.