A new learning paradigm enhances RVFL networks with better generalization.
problem Improving the generalization performance of RVFL networks.
method Integrates LUPI paradigm into RVFL networks, introduces KRVFL+.
result Proposed RVFL+ achieves better generalization performance than state-of-the-art methods.
This work tackles missing annotations in large sensor datasets.
problem Missing annotations in large sensor datasets negatively affect supervised learning system performance.
method Proposes and evaluates three paradigms to handle gaps: dropping, single label, and unique label, along with a hybrid combination.
result Evaluation of proposed paradigms and hybrid combination shows significant performance improvement.
This review explores resampling techniques for imbalanced binary classification.
problem Imbalanced classes lead to poor prediction results in classification.
method Classical, cost-sensitive, and Neyman-Pearson paradigms with resampling techniques and classification methods.
result Complex dynamics among resampling techniques, base methods, metrics, and imbalance ratios.
The paper proposes new interpretability paradigms to improve model faithfulness.
problem Improving the accuracy of explanations for complex models.
method Examining and evolving existing paradigms, proposing new models.
result Three new paradigms for interpretability are presented.
This research formalizes inductive generalization and proposes a new learning paradigm called Inductive Learning.
problem Generalization from easy to hard tasks, especially out-of-domain generalization.
method Formalizes inductive generalization, introduces Inductive Learning, and outlines steps to adapt techniques for learning model successors.
result A new learning paradigm (Inductive Learning) that emphasizes induction and universal properties of learning and computation.
MapLUR uses deep learning on map images to estimate NO2 pollution, outperforming traditional methods.
problem Limited availability of data for traditional LUR models makes them hard to adapt to new areas.
method Data-driven, open-source approach using convolutional neural networks trained on map data.
result MapLUR significantly outperforms traditional LUR models, including those with manually engineered features.
Proposes a new stock prediction method that accounts for market dynamics.
problem The dynamic nature of the stock market invalidates traditional machine learning assumptions.
method Develops a second-order learning paradigm with multi-scale patterns.
result Demonstrates effectiveness in stock prediction on real-world data.
Paper explores limits of distributed dislocations in geometric and constitutive paradigms.
problem Understanding limits of distributed dislocations in geometric and constitutive paradigms.
method Review and comparison of geometric and constitutive paradigms, analysis of edge dislocations in both paradigms.
result Homogenization theories in geometric and constitutive paradigms are consistent and identical in the case of constitutive relations having discrete symmetries.
Paper proposes SPO paradigm for better portfolio optimization in real markets.
problem Real-world trading frictions and constraints affect portfolio optimization quality.
method SPO paradigm with decision-focused training using surrogate loss and linear predictors.
result Decision-focused training improves risk-adjusted performance and robustness.
Proposes a method to adapt to new classes in a domain shift.
problem Learning new classes in a domain shift without labeled supervision.
method Inspired by prototypical networks, the method classifies target samples into shared and novel classes.
result Superior performance compared to DA and CI methods in the CIDA paradigm.
Federated Collaborative Filtering preserves user privacy in recommendation systems.
problem Preserving user privacy in machine learning models.
method Federated Learning approach with stochastic gradient updates.
result Collaborative filtering can be successfully federated without accuracy loss.
Enhances data programming with continuous labeling functions for better model performance.
problem Scarcity of labeled data hampers supervised learning models.
method Integrates continuous scoring functions and quality guides into a generative model to improve data programming reliability.
result Continuous labeling functions lead to improved recall and more stable model performance.
Since its inception, the modus operandi of multi-task learning (MTL) has been to minimize the task-wise mean of the empirical risks. We introduce a generalized loss-compositional paradigm for MTL that includes a spectrum of formulations as a subfamily. One endpoint of this spectrum is minimax MTL: a new MTL formulation…
Combines k-NN and RVM for improved classification accuracy.
problem Improving k-NN's performance by considering relevancy.
method Integrates k-NN and RVM in kernel space, introduces a new stopping parameter.
result Significantly prunes irrelevant attributes and improves classification accuracy.
Brain computer interfaces (BCI) enable direct communication with a computer, using neural activity as the control signal. This neural signal is generally chosen from a variety of well-studied electroencephalogram (EEG) signals. For a given BCI paradigm, feature extractors and classifiers are tailored to the distinct ch…
Paper adapts Bayesian Hui-Walter method for unlabeled data.
problem Lack of labeled data in machine learning.
method Adapted Hui-Walter paradigm for online, unlabeled data.
result Estimates performance metrics without labeled data.
Crowdsourced wisdom improves causal learning.
problem Improving causal learning through collective intelligence.
method Crowdsourcing, expert knowledge elicitation, aggregation techniques, and LLMs.
result Collective contributions enhance global causal structure.
Study on teaching reinforcement learning with Q-learning, reducing sample complexity.
problem Reducing sample complexity in reinforcement learning.
method Characterized teaching dimension for Q-learning under different teacher control, presented optimal teaching algorithms.
result Minimum number of samples needed for reinforcement learning is characterized.
Blockchain as a Service offers a secure, decentralized computing solution.
problem Lack of transparency, security, and privacy in cloud computing.
method Decentralized cooperative computing process using blockchain, homomorphic encryption, and SDN.
result Performance evaluated via different scenarios in simulations.
Graph Polish optimizes molecular structures by minimizing changes and maximizing preservation.
problem Error-prone traditional molecular optimization methods.
method Graph Polish transforms optimization into a polishing task, focusing on optimization centers and minimizing changes.
result Significant advantage over state-of-the-art methods on multiple optimization tasks.
This work introduces online meta-learning, merging paradigms to enhance continual learning.
problem Continuous learning of new tasks with fast adaptation.
method Follow the meta leader algorithm, extending MAML to online setting with theoretical guarantees.
result Significant performance improvement over traditional online learning approaches.
Study compares RL and SL for TSP, finds RL better for variable graph sizes.
problem Training deep neural networks for the Travelling Salesman Problem.
method Controlled experiments with supervised and reinforcement learning models on fixed and variable sized graphs.
result Reinforcement learning leads to better generalization to variable graph sizes.
KFServing simplifies serverless machine learning model deployment.
problem Autoscaling and cost management for machine learning models.
method KFServing project on KNative serverless platform.
result Consistent and simple interface for data scientists to deploy models.
Adjoined Networks trains both base and compressed networks together for efficient model compression.
problem Efficiently compressing deep neural networks while maintaining accuracy.
method Adjoined Networks (AN) trains both a base network and a smaller compressed network simultaneously, sharing parameters.
result AN achieves 71.8% top-1 accuracy with 1.8M parameters and 1.6 GFLOPs on ImageNet.
Theoretical justification for asymmetric actor-critic algorithms in reinforcement learning.
problem Lack of precise theoretical justification for asymmetric actor-critic algorithms in reinforcement learning.
method Adapting a finite-time convergence analysis to the asymmetric actor-critic setting with linear function approximators.
result A finite-time bound reveals that the asymmetric critic eliminates aliasing errors in the agent state.
New method improves language model fine-tuning without forgetting.
problem Fine-tuning language models to match specific distributions without forgetting.
method Combines Distribution Matching and Reinforcement Learning techniques.
result Adding a baseline improves constraint satisfaction, stability, and efficiency.
Combines cost-sensitive and Neyman-Pearson paradigms for better binary classification.
problem Asymmetric binary classification problems with unequal error severities.
method Develops TUBE-CS algorithm to bridge cost-sensitive and Neyman-Pearson paradigms.
result High-probability control of population type I error.
We present two paradigms relating algebraic, topological and quantum computational statistics for the topological model for quantum computation. In particular we suggest correspondences between the computational power of topological quantum computers, computational complexity of link invariants and images of braid grou…
Data science models, although successful in a number of commercial domains, have had limited applicability in scientific problems involving complex physical phenomena. Theory-guided data science (TGDS) is an emerging paradigm that aims to leverage the wealth of scientific knowledge for improving the effectiveness of da…
We propose a paradigm to deep-learn the ever-expanding databases which have emerged in mathematical physics and particle phenomenology, as diverse as the statistics of string vacua or combinatorial and algebraic geometry. As concrete examples, we establish multi-layer neural networks as both classifiers and predictors …
Deep ReLU networks can approximate matrix-vector products with error bounds.
problem Can deep ReLU networks accurately approximate matrix-vector products?
method Derived error bounds in Lebesgue and Sobolev norms for deep ReLU FNNs.
result Developed deep approximation theory with successful applications.
We propose a general information-theoretic approach called Seraph (SEmi-supervised metRic leArning Paradigm with Hyper-sparsity) for metric learning that does not rely upon the manifold assumption. Given the probability parameterized by a Mahalanobis distance, we maximize the entropy of that probability on labeled data…
We present a new paradigm for speeding up randomized computations of several frequently used functions in machine learning. In particular, our paradigm can be applied for improving computations of kernels based on random embeddings. Above that, the presented framework covers multivariate randomized functions. As a bypr…
Paper compares AutoML methods for recommending classification algorithms.
problem Finding the best classification algorithm for a dataset.
method Four AutoML methods using Evolutionary Algorithms and CASH approach.
result EA-based methods, especially decision-tree induction, produce interpretable models.
Novel co-learning method for manifolds with group actions using multiple fibre bundles.
problem Learning from manifolds with group actions without labeled data.
method Representation theory to associate multiple fibre bundles, leveraging group actions for unsupervised learning.
result Improved robust nearest neighbor search and community detection on cryo-electron microscopy images.
A new learning method uses data to learn from large model sets.
problem Learning with large sets of candidate models where uniform convergence is hard.
method Data-dependent learning that incorporates empirical data less reliant on prior assumptions.
result Demonstrates improved generalization in various learning assumptions.
Curious hierarchical reinforcement learning improves learning performance.
problem Combining hierarchical abstraction and curiosity-driven exploration in reinforcement learning.
method Developed a method that combines hierarchical reinforcement learning with curiosity.
result Curiosity can more than double learning performance and success rates.
Paper uses SVM+ for valid prediction intervals in drug discovery datasets.
problem Valid prediction intervals in drug discovery datasets.
method LUPI paradigm, SVM+, inductive conformal predictor.
result Valid prediction intervals at specified significance levels.
Unified framework for multi-objective curriculum learning in robotics.
problem Improving sample efficiency and final performance in robotic policy learning.
method Unified automatic curriculum learning framework with multi-task hyper-net and flexible memory mechanism.
result Superior performance compared to state-of-the-art methods in robotic manipulation tasks.
New framework uses unsupervised learning for efficient exploration in RL.
problem Efficient exploration in reinforcement learning with rich observations.
method Combines unsupervised learning and no-regret RL algorithms.
result Proves sample complexity for finding near-optimal policies.
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.
Self-supervised learning improves representation from EEG signals without labels.
problem Limited supervised data for EEG signal analysis.
method Predicting temporal context from unlabeled EEG time series.
result Self-supervised approach outperforms supervised methods in low data regimes.
Study compares symbolic and distributional methods for relational learning.
problem Comparing symbolic and distributional paradigms for relational learning.
method Comparison of representation learning and relational learning on various tasks.
result Preliminary results suggest possible indicators for choosing between approaches.
New algorithm reduces individual regret and communication costs in cooperative bandits.
problem Optimal individual and group regret in cooperative multi-agent bandits.
method Integrates a new communication policy into a learning algorithm.
result Achieves optimal individual regret and constant communication costs.
This study improves GANs by learning latent distributions and pushforward maps.
problem Improving the performance of GANs with optimal transport metrics.
method Focuses on the interplay between latent distribution and generator complexity.
result Learning latent distributions and pushforward maps can significantly reduce sample complexity.
Paper proposes verifier engineering for improving foundation models.
problem Challenges in providing effective supervision signals for foundation models.
method Leverages automated verifiers to perform verification tasks and deliver feedback.
result Verifier engineering can enhance foundation models' capabilities.
Report on challenges and approaches for Multi-Agent RL.
problem Challenges in Multi-Agent RL for cooperative and competitive environments.
method Decentralized Actor, Centralized Critic approach based on Decentralized Partially Observable MDPs.
result Advances in Multi-Agent RL for mixed cooperative and competitive environments.
Neuromorphic column performs online unsupervised clustering.
problem Real-time clustering of streaming data.
method Localized, spike timing-dependent plasticity (STDP) neural column.
result Prototype column performs similarly to k-means clustering.