Minimalistic unsupervised learning with sparse manifold transform achieves SOTA performance.
problem Achieving state-of-the-art unsupervised learning performance without complex engineering.
method Sparse manifold transform, leveraging sparse coding, manifold learning, and slow feature analysis.
result 99.3% KNN top-1 accuracy on MNIST, 81.1% on CIFAR-10, and 53.2% on CIFAR-100.
In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two different feature extraction methods. In our design, Stacked-convolutional (SC) and Residual-connecte…
Machine learning has played an important role in information retrieval (IR) in recent times. In search engines, for example, query keywords are accepted and documents are returned in order of relevance to the given query; this can be cast as a multi-label ranking problem in machine learning. Generally, the number of ca…
Clarifies contributions of model architectures and resources in SOTA language models.
problem Difficulty in disentangling contributions of model architectures and resources.
method Overview of large pre-trained language models, focusing on their use of new architectures and resources.
result Identifies potential starting points for benchmark comparisons and areas for improvement.
Diffusion models generate private synthetic images with high quality.
problem Generating private synthetic images from sensitive datasets.
method Differentially private fine-tuning of pre-trained diffusion models.
result Improved synthetic data quality and accuracy compared to non-private models.
New method defends against both single-step and iterative adversarial examples.
problem Defending against adversarial examples, especially iterative ones, is computationally expensive.
method Single-Step Adversarial Training (SST) with modifications.
result Our method outperforms state-of-the-art methods in both accuracy and training time.
New methods use Kronecker-factored approximations for faster deep learning optimization.
problem Optimizing deep learning models with rich curvature information.
method Approximate Hessian using Kronecker products for efficient quasi-Newton methods.
result New methods outperform first-order methods and perform comparably to second-order methods.
Optimal quantization improves dataset distillation for faster training.
problem Efficiently train models with synthetic data.
method Reformulate disentangled methods as optimal quantization problems.
result Better performance and generalization on ImageNet-1K and subsets.
New KWS neural networks improve accuracy and power efficiency.
problem Maximizing accuracy and power efficiency in KWS systems.
method Hardware Aware Training (HAT) for LMU-based neural networks.
result Achieved state-of-the-art accuracy and low parameter counts.
Simpler GNNs with low-rank non-parametric aggregators perform well on graph benchmarks.
problem Over-engineering in GNN architectures for common semi-supervised node classification datasets.
method Replacing feature aggregation with a non-parametric learner to streamline GNN design.
result Non-parametric regression is effective for semi-supervised learning on sparse, directed networks.
Improved DP-SGD on large models achieves high accuracy on image classification tasks.
problem Differentially private image classification often degrades performance.
method Careful hyper-parameter tuning and signal propagation techniques.
result Achieved 81.4% top-1 accuracy on CIFAR-10 under (8, 10^{-5})-DP.
Paper proposes faster certified robust training methods with short warmup.
problem Certified robust training methods require long warmup schedules, making training costly.
method Proposes three improvements: new weight initialization, BN, and regularization.
result Achieves 65.03% verified error on CIFAR-10 and 82.36% on TinyImageNet with short warmup.
BeBold improves exploration in sparse-reward tasks by regulating visitation counts.
problem Efficient exploration in deep reinforcement learning under sparse rewards.
method Regulated difference of inverse visitation counts.
result BeBold solves 12 challenging tasks in MiniGrid with fewer steps than previous state-of-the-art.
Researchers parallelize neural kernels for large-scale data, achieving state-of-the-art accuracy.
problem Limited scalability of neural kernels on large datasets.
method Massively parallel computation across many GPUs, combined with a distributed, preconditioned conjugate gradients algorithm.
result Achieved state-of-the-art accuracy of 91.2% on CIFAR-5m dataset using neural kernels.
This work tackles uncertainty in multi-agent multi-modal trajectory forecasting.
problem Measuring and ranking uncertainty in multi-agent multi-modal trajectory forecasting.
method Proposes collaborative uncertainty (CU) and a CU-aware regression framework.
result The CU-aware regression framework improves SOTA systems' performances.
New algorithm improves tensor completion performance.
problem Tensor completion for partially observed data.
method Adaptive ADMM optimization framework for low-rank tensor completion.
result New method outperforms conventional techniques in NMSE.
Double InfoGAN improves CA by generating clearer, more accurate images.
problem Improper latent variable models in CA lead to sub-optimal solutions.
method Double InfoGAN, a GAN-based method enforcing fundamental assumptions and improving image quality.
result Double InfoGAN outperforms SOTA CA-VAEs in latent separation and image quality.
A new clustering algorithm GDT improves on HDBSCAN for uneven data.
problem Data clustering with uneven distribution and high noise.
method GDT combines local and global structures, forming local clusters and estimating a global topological graph based on connectivity between clusters.
result GDT achieves SOTA performance on various datasets with low time complexity.
We simplify diffusion models by defining a design space and improving FID scores.
problem Complexity in diffusion-based generative models.
method Defined a design space, improved sampling and training processes, and pre-conditioned score networks.
result Improved FID scores of 1.79 for CIFAR-10 and 1.97 for unconditional settings.
Unified principle LZN unifies generative modeling, representation learning, and classification.
problem Disjoint solutions for generative modeling, representation learning, and classification.
method LZN creates a shared latent space for all tasks, using encoders and decoders for each data type.
result LZN improves FID on CIFAR10 and outperforms existing methods in representation learning and joint generation/classification.
RLD improves combinatorial optimization by avoiding local minima.
problem Efficiently solving combinatorial optimization problems.
method Regularized Langevin Dynamics (RLD) for combinatorial optimization.
result RLD achieves comparable or better performance than previous methods.
SA-Solver improves stochastic sampling from DPMs.
problem Efficient sampling from Diffusion Probabilistic Models (DPMs) is time-consuming.
method Proposes SA-Solver, an improved stochastic Adams method for solving diffusion SDE.
result SA-Solver achieves improved or comparable performance compared to SOTA methods for few-step sampling.
Improved neural active learning algorithms reduce regret and improve performance.
problem Improving performance and reducing regret in neural active learning for non-parametric streaming data.
method Introducing two new regret metrics and leveraging NNs for both exploitation and exploration. The algorithm uses tailored query decision-makers and full feedback.
result Achieved an instance-dependent regret upper bound improving by a multiplicative factor of O(logT) and removing the curse of dimensionality. TabPFN-3 scales tabular prediction models to large datasets and improves performance and speed.
problem Scaling tabular prediction models to large datasets with high performance and efficiency.
method Pretrained on synthetic data, introduces test-time compute scaling, and uses row-chunking.
result Significantly outperforms other models on TabArena and diverse datasets.
New method aggregates Gaussian experts by detecting conditional independence violations.
problem Aggregation of dependent Gaussian experts leads to sub-optimal solutions.
method Uses Gaussian graphical model to detect and correct conditional independence violations.
result Improves aggregation of Gaussian experts, outperforming SOTA DGP approaches.
MET learns tabular data representations without data augmentations.
problem Lack of effective self-supervised learning methods for tabular data.
method Reconstruction-based approach using masked encoding, with separate representations for each coordinate and adversarial reconstruction loss.
result MET achieves state-of-the-art performance on five diverse tabular datasets, improving up to 9% over current methods.
Improves scalability and efficiency of mixture models in black-box variational inference.
problem Scaling mixture models in black-box variational inference leads to high parameter and time costs.
method Introduces MISVAE for amortized mixture parameter space and new ELBO estimators.
result Achieves superior estimation performance with fewer parameters and shorter inference time.
Improved SNNs with quantized activations outperform traditional networks.
problem Maintaining SotA accuracy in SNNs with limited bit precision.
method Interpolating between non-spiking and spiking regimes using signal processing tools.
result First hybrid SNN outperforms traditional RNNs in accuracy with reduced bit precision.
Robots' agility in changing terrain helps financial models adapt to market shifts.
problem Challenges in financial market forecasting due to regime switching.
method Adapts pretrained LLMs using intrinsic market rewards and reinforcement learning.
result Significantly improved accuracy in adapting to market regime shifts.
A new data-level recombination strategy improves RGB-D salient object detection.
problem RGB-D salient object detection struggles with depth information.
method Proposes a novel data-level recombination strategy to fuse RGB and depth data before feature extraction.
result Achieves a new state-of-the-art performance in RGB-D salient object detection.
PHLP uses persistent homology to interpret graph link prediction.
problem Interpreting why graph neural network models perform well in link prediction.
method Employing persistent homology to analyze graph topology and extract features.
result PHLP outperforms state-of-the-art models on most benchmark datasets.
Paper develops efficient recursive learning for multi-channel systems with heterogeneous dynamics.
problem Accurately learning system dynamics in complex, multi-channel systems with nonlinear and noisy data.
method Formulates system as Gaussian process state-space models (GPSSMs), introduces heterogeneous multi-output kernel, and develops recursive inference framework.
result Matches SOTA offline GPSSMs in accuracy with 1/100 runtime, and outperforms SOTA online GPSSMs by 70% in accuracy under noise with 1/20 runtime.
BlockEcho method improves imputation of block-wise missing data.
problem Block-wise missing data reduces interpolation capability and predictive power.
method Integrates Matrix Factorization (MF) within Generative Adversarial Networks (GAN) to retain long-distance inter-element relationships.
result Superior performance on public datasets across three domains, especially at higher missing rates.
Private training and synthetic data generation using DP clustering.
problem Protecting sensitive data in deep neural networks training.
method Approximate input dataset with privately generated synthetic dataset using DP clustering.
result Simple two-layer neural network achieves SOTA classification accuracy on standard benchmark datasets.
The paper bridges theory and practice in query-driven selectivity learning.
problem Insufficient theoretical understanding of query-driven selectivity learning.
method Demonstrates learnability of selectivity predictors and establishes favorable OOD generalization error bounds.
result Theoretical advances improve OOD generalization of query-driven selectivity models.
New method improves OOD detection by integrating diffusion models into discriminator models.
problem Overconfidence in discriminator models leads to poor OOD detection.
method Integrates diffusion models into discriminator and generation models to mitigate overconfidence.
result Demonstrates significant improvement in AUROC scores for challenging datasets.
Recent object detectors use four-coordinate bounding box (bbox) regression to predict object locations. Providing additional information indicating the object positions and coordinates will improve detection performance. Thus, we propose two types of masks: a bbox mask and a bounding shape (bshape) mask, to represent t…
TeLeS improves ASR confidence estimation by considering temporal alignment and lexical errors.
problem Inaccurate confidence scores from E2E ASR models, especially for overconfident predictions.
method Proposes TeLeS, a novel confidence score that considers temporal alignment and lexical errors, and uses shrinkage loss to handle data imbalance.
result TeLeS generalizes well across different languages and ASR models, leading to significant WER reduction.
New method for multi-modal depth prediction challenges.
problem Challenges in applying unimodal coreset selection to multi-modal data.
method Adapted state-of-the-art coreset selection technique for multimodal data.
result Challenges in extending unimodal algorithms to multi-modal scenarios.
WebGUM learns web navigation from multimodal data, outperforming previous methods.
problem Limited generalization from domain-specific models in web navigation.
method Instruction-following multimodal agent trained on vision-language foundation models.
result Significant improvement in web navigation performance on benchmarks.
SubTab turns tabular data into a multi-view problem for better representation learning.
problem Lack of structure in tabular data makes it hard to apply effective self-supervised learning methods.
method Divides tabular features into subsets and uses autoencoder-like reconstruction for collaborative inference.
result SubTab achieves state-of-the-art performance on tabular datasets, matching or surpassing CNN-based methods.
A new mutual information optimization method using self-supervised binary contrastive learning.
problem Improving self-supervised contrastive learning for better model performance.
method Proposes a novel loss function for contrastive learning that optimizes mutual information in positive and negative pairs.
result The proposed method outperforms state-of-the-art self-supervised contrastive frameworks on various benchmark datasets.
AI agent learns to handle unknown unknown states in reinforcement learning.
problem Handling unexpected, previously unseen states in reinforcement learning.
method Proposes EMDP-GA model with NIVE approach to expand value functions.
result Asymptotically consistent regret and comparable computational complexity.
New model improves recommendation systems by analyzing user-item interactions.
problem Improving recommendation systems for better user-item interactions.
method Sliced Anti-symmetric Decomposition (SAD) model using tensor decomposition.
result SAD produces the most consistent personalized preferences compared to SOTA models.
AutoShrink optimizes neural architectures by shrinking cell structures.
problem Resource constraints in deploying DNNs on mobile devices.
method Topology-aware node-based Neural Architecture Search (NAS).
result AutoShrink achieves up to 48% parameter reduction and 34% MACs savings.
CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.
problem Interpreting dynamic human decision-making processes in medical contexts.
method Develops Contextualized Policy Recovery (CPR) framework for multi-task learning, modeling each context-specific policy as a linear map.
result Achieves state-of-the-art performance in predicting medical decisions, closing the gap between interpretable and black-box methods.
INFERS PDEs from data samples using learned context.
problem Inferring explicit PDEs from unseen dynamics.
method Contextual Finite Differences (CFD) method integrating PDE form and differential scheme.
result Yields a PDE fitting the data sample for signal prediction and explanation.
This research uses deep learning to automatically classify UN resolutions.
problem Manual labeling of UN documents is too time-consuming.
method Utilizes pre-trained deep learning models without traditional training.
result Shows effectiveness in classifying UN resolutions by SDGs.