This paper explores how optimizing data access and reducing redundancy can improve machine learning algorithm performance.
problem Performance issues in machine learning algorithms due to data locality and redundancy.
method Analysis of data access patterns and computational redundancy in machine learning algorithms, identifying opportunities for reuse and experimentation.
result Initial indicative results show potential for improving performance through data access optimization and reuse of computation results.
Paper develops AGLD for MCMC with bounds for various data access strategies.
problem Efficient MCMC sampling for large-scale Bayesian posterior learning.
method Aggregated Gradient Langevin Dynamics framework with unified analysis.
result Unified bounds for cyclic access and random reshuffle strategies.
This paper proposes faster machine learning by reducing data access time.
problem Slow training times due to large datasets or feature sizes.
method Systematic and cyclic sampling techniques to reduce data access time.
result Proven to reduce training time up to six times with empirical validation.
GrateTile optimizes CNN feature map storage for efficient data access.
problem Efficient storage and access of sparse CNN feature maps.
method Divides feature maps into uneven-sized subtensors, compresses and stores them in a compressed yet accessible format.
result Average 55% DRAM bandwidth reduction with minimal indexing overhead.
In this paper we propose a framework for automated forecasting of energy-related time series using open access data from European Network of Transmission System Operators for Electricity (ENTSO-E). The framework provides forecasts for various European countries using publicly available historical data only. Our solutio…
LLMs help less-resourced researchers access costly data.
problem Unequal access to costly datasets limits research contributions.
method RAG framework with GPT-4o-mini for automated data collection.
result LLMs can collect CEO pay ratios and CAMs from corporate disclosures with high accuracy and low cost.
Satellite imagery and ML improve livelihood measurements and estimate electrification's impact.
problem Sparse data hinders policy development and evaluation.
method Satellite imagery, machine learning, and ML inference techniques.
result Grid access improves rural asset wealth by 0.17 standard deviations.
RealMix improves SSL performance with real-world data challenges.
problem Poor SSL performance when labeled and unlabeled data distributions differ.
method Develops RealMix, a new SSL algorithm.
result Achieves state-of-the-art results on standard benchmark datasets.
Paper tackles structure learning of sparse GGMs over multiple access networks.
problem Estimating sparse Gaussian Graphical Model structure from multiple local machines with limited communication.
method Proposes Signs and Uncoded methods for reliable structure learning under power and bandwidth limitations.
result Both methods can recover the structure with high probability for large enough sample size.
Deep learning and set theory improve prediction accuracy regardless of data relevance.
problem Improving prediction accuracy with limited relevant training data.
method Deep learning and set theory applied to large labeled training data.
result Exceptional prediction results achieved with irrelevant training data.
Framework reuses pre-trained models for data-free transfer learning.
problem Challenges in retrieving source data for model training.
method Model Recycling Framework for parameter-efficient training.
result Makes multi-source data-free supervised transfer learning possible.
Role mining tackles the problem of finding a role-based access control (RBAC) configuration, given an access-control matrix assigning users to access permissions as input. Most role mining approaches work by constructing a large set of candidate roles and use a greedy selection strategy to iteratively pick a small subs…
Quantum models can approximate any function if data encoding allows for a rich enough frequency spectrum.
problem Theoretical properties of quantum machine learning models, particularly their expressive power.
method Investigated how data encoding affects the expressive power of parametrized quantum circuits.
result Quantum models can access increasingly rich frequency spectra by repeating data encoding gates, potentially making them universal function approximators.
The FAIRnets Ontology makes neural networks findable, accessible, interoperable, and reusable.
problem The resource-intensive training of neural networks and the lack of training data availability.
method Development of FAIRnets Ontology to model neural networks on a meta-level and creation of a knowledge graph (FAIRnets) of over 18,400 neural networks.
result The FAIRnets Ontology and knowledge graph enable the reuse and recommendation of neural networks to data scientists.
Study creates open-access wildfire dataset for Russia.
problem Data scarcity for comprehensive Eurasian wildfire research.
method Machine learning for exploratory data analysis and predictive modeling.
result Identified key environmental factors influencing fire behavior.
Paper speeds up IoT device detection and data decoding.
problem Efficiently detect and decode massive IoT devices in grant-free random access.
method Develops multi-armed bandit approaches for more efficient detection via coordinate descent.
result Proposed bandit based algorithms achieve faster convergence rates with lower time complexity.
FinGPT is an open-source financial LLM for democratizing financial data.
problem Accessing high-quality financial data for LLMs.
method Data-centric approach with automatic data curation and low-rank adaptation.
result FinGPT provides accessible and transparent financial data for FinLLMs.
Multi-party machine learning leaks global dataset properties even with black-box access.
problem Leakage of global dataset properties in multi-party machine learning.
method Demonstrated leakage of sensitive attribute distributions in pooled data.
result A curious party can infer sensitive attribute distributions in other parties' data with high accuracy.
Interactive book integrates probability models with big data analytics.
problem Lack of integration between classical loss data models and modern analytic tools.
method Combines classical loss data models with modern analytic tools and big data.
result Promotes deeper learning through interactive elements and multiple language support.
A new method for unlearning trained models without needing the original data.
problem Lack of access to original training data for privacy-preserving unlearning.
method Uses a surrogate dataset to approximate statistical properties and calibrates noise based on statistical distance.
result Effective unlearning of trained models with strong privacy guarantees, even without access to the original data.
Parrot learns optimal cache replacement policies using imitation learning.
problem Improving cache hit rates in complex access patterns.
method Imitation learning approach using Belady's oracle policy.
result Parrot increases cache hit rates by 61% on a web search benchmark.
New algorithm SAGA++ improves on SAGA for faster convergence in stochastic batch size methods.
problem Optimizing convergence rate in stochastic variance reduction methods with batch size.
method Proposes SAGA++ algorithm with optimal average batch size considering cache/disk IO effects.
result SAGA++ outperforms SAGA and other solvers on real datasets.
A novel Gradient-Based Multiple Access algorithm for distributed learning over fading channels.
problem Distributed learning over multiple access fading channels.
method Gradient-Based Multiple Access (GBMA) algorithm, using analog gradients and common shaping waveforms.
result GBMA can approach the convergence rate of centralized gradient descent in large networks.
We perform the first study of the tradeoff space of access methods and replication to support statistical analytics using first-order methods executed in the main memory of a Non-Uniform Memory Access (NUMA) machine. Statistical analytics systems differ from conventional SQL-analytics in the amount and types of memory …
This paper enhances ML algorithms by improving data locality and reducing redundancy.
problem Improving performance of machine learning algorithms with complex data.
method Exploiting data locality and reuse in memory hierarchies of modern processors.
result Efficient implementation of machine learning algorithms can be achieved by reusing computation results.
MIMIC-Extract transforms EHR data for reproducible healthcare machine learning.
problem Lack of accessible, standardized healthcare data for machine learning.
method Open-source pipeline for converting raw EHR data into usable dataframes.
result Demonstrates utility through benchmark tasks and baseline results.
Classical clients can verify quantum learning tasks efficiently.
problem Making quantum learning accessible to classical clients.
method Developed a framework for classical verification of quantum learning.
result Quantum learning tasks can be efficiently verified by classical verifiers.
New methods protect privacy while providing accurate prediction sets.
problem Privacy-preserving conformal prediction for untrusted aggregators.
method Two LDP approaches: k-ary randomized response and binary search response.
result Finite-sample coverage guarantees and robust coverage under randomization.
This paper proposes a new estimation algorithm for the parameters of an HMM as to best account for the observed data. In this model, in addition to the observation sequence, we have \emph{partial} and \emph{noisy} access to the hidden state sequence as side information. This access can be seen as "partial labeling" of …
New attacks steal ML models via public APIs, even with confidence values.
problem Stealing confidential ML models via public APIs.
method Simple, efficient attacks that extract target ML models with near-perfect fidelity.
result Natural countermeasure of omitting confidence values from model outputs still admits harmful attacks.
New algorithm reduces data access and complexity for big data problems.
problem Efficiently solving problems with large numbers of samples in ultra-high dimensional space.
method Accelerated Variance Reduced Block Coordinate Descent (AVRBCD)
result Achieves an accelerated convergence rate of O(1/k^2) with low per-iteration complexity.
Proposes using probabilistic models for privacy-preserving synthetic data.
problem Designing high-quality synthetic data for privacy preservation.
method Formulate the problem through probabilistic modelling, choosing a model for the data.
result Statistical discoveries can be reliably reproduced from synthetic data.
New method uses synthetic data to validate financial agent classification.
problem Validation of machine learning methods for financial agent classification.
method Agent-based model to generate synthetic data for validation.
result Unsupervised clustering may give incorrect results for financial agents.
Bayesian method learns from aggregated quantile data.
problem Limited access to sensitive personal data.
method Bayesian quantile matching estimation based on order statistics.
result Correctly reflects uncertainty of empirical quantiles.
Theorem ensures superior learning outcomes for authorized learners with quantum label encoding.
problem Ensuring data security for authorized learners in machine learning.
method Quantum label encoding and PAC learning framework.
result Authorized learners achieve superior learning outcomes while eavesdroppers do not.
Private method measures nonlinear correlations between data hosted across two entities.
problem Measuring nonlinear correlations between sensitive data hosted across multiple parties while preserving privacy.
method Differentially private estimator of distance correlation.
result First private estimator of nonlinear correlations in a multi-party setup.
Generative models learn from biased data using weighted importance.
problem Learning from biased or related data distributions.
method Importance weighting to estimate loss with respect to target distribution.
result Effective in various settings with theoretical guarantees and good performance.
WAFFLE embeds watermarks in federated learning models without access to training data.
problem Model theft in federated learning due to lack of centralized control.
method Retraining step at server after model aggregation, generating backdoor as watermark.
result Efficient embedding of resilient watermark with negligible accuracy loss.
Bayesian models evaluate sentence comprehension, showing direct access model fits data better.
problem Evaluating models of retrieval in sentence comprehension.
method Implemented Bayesian hierarchical models to compare activation-based and direct access models.
result Direct access model fits data better than activation-based model.
ModHiFi identifies critical components for model modification without gradients or loss function.
problem Modifying open weight models without access to training data or loss function.
method Theoretical analysis of Lipschitz-continuous networks, Subset Fidelity metric, and ModHiFi algorithm.
result ModHiFi-P and ModHiFi-U achieve significant performance improvements in model pruning and unlearning.
Optimal DP model training with public data improves privacy and accuracy.
problem Ensuring privacy while training models with public data.
method Proves optimal error rates for DP model training with public data, develops novel algorithms.
result Optimal error rates can be achieved by using public data or optimal DP algorithms.
Proposes a new method to selectively access privileged information in reinforcement learning.
problem Selective compression of privileged information in reinforcement learning.
method Formulates a variational bandwidth bottleneck to decide stochastically whether to access privileged information.
result Improves generalization and reduces access to costly information in reinforcement learning experiments.
Paper proposes detecting OOD examples using Gram matrices and in-distribution data.
problem Detecting OOD examples with confidence and without OOD data.
method Characterize activity patterns with Gram matrices and identify anomalies in values.
result High OOD detection rates achieved without OOD data.
Study develops sign recognition system for DHH users.
problem Accessibility of voice-controlled devices for Deaf and Hard-of-Hearing users.
method Multimodal data (RGB video and skeletal data) for sign language recognition using deep learning.
result Validation on GMUASL51 dataset of 12 users and 13107 samples across 51 signs.
Proposes a deep reinforcement learning framework for dynamic multichannel access.
problem Efficient use of limited spectral resources in dynamic multichannel access.
method Deep actor-critic reinforcement learning framework for both single-user and multi-user scenarios.
result Demonstrates improved performance and adaptive ability compared to existing methods.
The study bounds curve sizes on surfaces using group cubulations.
problem Bounding curves on surfaces.
method Group cubulations and acylindrical accessibility.
result Bounds on curves on surfaces.
New attack method makes poisoned images transferable without access to victim model.
problem Injecting poisoned images into training data to mislead deep nets.
method Designing poison images to surround targeted images in feature space, using Dropout.
result Achieves over 50% transferable success with only 1% poisoning of training set.
Improved sample complexity for diffusion models without needing empirical risk minimizers.
problem Theoretical limitations in sample complexity for diffusion models.
method Structured decomposition of score estimation error, eliminating dependence on neural network parameters.
result Achieved sample complexity bound of O(ε^(-4)) without empirical risk minimizer access.