Simplified image clustering achieves competitive results without text-based embeddings.
problem Complexity and resource requirements of state-of-the-art clustering methods.
method SCP: trains a small cluster head using pre-trained vision model features and positive data pairs.
result SCP achieves highly competitive performance on various benchmark datasets.
The paper simplifies Bayesian posterior using clustering to make inference more manageable.
problem Handling large-scale, redundant datasets in Bayesian learning.
method Construct an approximate posterior by replacing data points in the same cluster with the centroid.
result The approximate posterior is close to the exact posterior and easier to sample from.
After being trained, classifiers must often operate on data that has been corrupted by noise. In this paper, we consider the impact of such noise on the features of binary classifiers. Inspired by tools for classifier robustness, we introduce the same classification probability (SCP) to measure the resulting distortion…
New method solves complex constrained optimization problems.
problem Constrained nonconvex-nonconcave minimax optimization problems.
method Inexact proximal gradient method using sequential convex programming.
result Established complexity guarantees for approximate stationary points.
FCM clustering adapts to persistence diagrams for topological data analysis.
problem Integrating topological data into machine learning workflows.
method Adapting Fuzzy c-Means to persistence diagrams.
result FCM clustering captures topological structure without additional processing.
Simplified trust region method reduces representation change during fine-tuning.
problem Stability and representational collapse in fine-tuning pre-trained models.
method Replaces adversarial objectives with parametric noise in trust region theory.
result Matches or exceeds previous trust region methods in performance and speed.
Numerous methods for computing conformal mesh paramterizations has been developed due to the vast applications in the field of geometry processing. Spectral conformal parameterization (SCP) is one of these methods to computing a quality conformal parameterization based on the spectral technique. SCP focus on a generali…
In this paper we study a broad class of structured nonlinear programming (SNLP) problems. In particular, we first establish the first-order optimality conditions for them. Then we propose sequential convex programming (SCP) methods for solving them in which each iteration is obtained by solving a convex programming pro…
BCI provides calibrated prediction intervals for time series forecasts.
problem Calibration of prediction intervals for time series forecasts.
method BCI wraps around any time series forecasting models and optimizes interval lengths using dynamic programming.
result BCI achieves long-term coverage under arbitrary distribution shifts and temporal dependence.
Clustering is a fundamental unsupervised learning approach. Many clustering algorithms -- such as k-means -- rely on the euclidean distance as a similarity measure, which is often not the most relevant metric for high dimensional data such as images. Learning a lower-dimensional embedding that can better reflect the …
Paper shows pre-training and transfer learning reduce sample complexity for neural networks.
problem Training high-dimensional supervised learning with limited labeled data.
method Study of single-layer neural networks via online stochastic gradient descent, considering concept shift.
result Pre-training and transfer learning reduce sample complexity by polynomial factors under general assumptions.
Graph neural networks (GNNs) are shown to be successful in modeling applications with graph structures. However, training an accurate GNN model requires a large collection of labeled data and expressive features, which might be inaccessible for some applications. To tackle this problem, we propose a pre-training framew…
This paper integrates LLMs into SCD to improve causal inference accuracy.
problem Challenges in acquiring domain expert knowledge for causal models.
method Statistical causal prompting (SCP) for LLMs and prior knowledge augmentation for SCD.
result LLM-KBCI and SCD augmented with LLM-KBCI approach ground truths more closely.
The study finds a theoretical bound for pre-training iterations needed for pruning to yield good subnetwork performance.
problem Discovering efficient subnetworks within pre-trained dense networks.
method Mathematical analysis of a two-layer, fully-connected network, validating with a multi-layer perceptron trained on MNIST.
result A logarithmically dependent threshold on dataset size for successful pruning.
The study improves prediction regions for hierarchical data using a projection step.
problem Improving prediction regions for hierarchical multivariate data.
method Integrating a projection step in the split conformal prediction (SCP) procedure to reduce prediction regions.
result The resulting prediction regions are globally smaller under both joint and component-wise coverage objectives.
Improved tabular models learn better from real-world data.
problem Tabular models perform poorly on real-world datasets when trained only on synthetic data.
method Continued pre-training on a curated set of real-world datasets.
result Real-TabPFN achieves superior predictive accuracy on 29 datasets.
To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and accelerate deep CNNs via channel pruning. Precisely, we argue that channels reveali…
Simplifies BO by directly sampling from posterior, achieving 35x efficiency.
problem Optimizing expensive functions with Bayesian Optimization.
method Direct sampling from posterior using a pre-trained generative model.
result Achieves 35x efficiency gain over Gaussian process-based BO.
The performance of most the clustering methods hinges on the used pairwise affinity, which is usually denoted by a similarity matrix. However, the pairwise similarity is notoriously known for its vulnerability of noise contamination or the imbalance in samples or features, and thus hinders accurate clustering. To tackl…
Transformers can learn spectral methods and perform unsupervised learning.
problem Learning spectral methods using unsupervised learning.
method Using multi-layered Transformers, pre-trained on a large set of instances, to learn and perform statistical estimation tasks.
result Proven that pre-trained Transformers can learn spectral methods and perform tasks like PCA and clustering.
Bayesian context trees capture complex dependencies in categorical sequences.
problem Complex, long-range dependencies in categorical sequences are not well captured by simple models.
method Parsimonious Bayesian context trees with model-based agglomerative clustering for efficient inference.
result The proposed framework outperforms existing models on real-world data.
We present two related methods for deriving connectivity-based brain atlases from individual connectomes. The proposed methods exploit a previously proposed dense connectivity representation, termed continuous connectivity, by first performing graph-based hierarchical clustering of individual brains, and subsequently a…
We define transit clusters to simplify causal diagrams and preserve their essential properties.
problem Clustering variables in causal diagrams can alter essential properties of causal effects.
method We define transit clusters and provide an algorithm to find them, ensuring they preserve causal effect identifiability.
result Transit clusters simplify causal effect identification and maintain their essential properties.
Ensemble pre-trained models for low data transfer learning.
problem Training good models from scratch in low data regime.
method Fine-tune nearest-neighbour ranked pre-trained models to create ensembles.
result Achieves state-of-the-art performance with lower inference budget.
Simplified non-contrastive learning avoids representation collapse.
problem Training failure modes in self-supervised learning.
method Hyperdimensional computing and inductive bias.
result The approach avoids representation collapses.
Paper develops a theory explaining contrastive pre-training for multimodal AI.
problem Limited theoretical understanding of contrastive pre-training for multi-modal AI.
method Introduces approximate sufficient statistics and Joint Generative Hierarchical Model.
result Near-minimizers of contrastive loss are approximately sufficient, enabling diverse downstream tasks.
Improved LLM pre-training performance through better weight and variance control.
problem Improper weight and variance control in LLM pre-training affects downstream task performance.
method Introduced Layer Index Rescaling (LIR) and Target Variance Rescaling (TVR) techniques.
result Substantial improvements in downstream task performance (up to 4.6%) and reduced extreme activation values.
Simplified A-polynomial calculation for twisted knots.
problem Calculating A-polynomials for twisted knots.
method Observation of exchange relations in cluster algebra and proof of Laurent phenomenon.
result Simplified method for calculating A-polynomials for twisted knots.
We introduce the State Classification Problem (SCP) for hybrid systems, and present Neural State Classification (NSC) as an efficient solution technique. SCP generalizes the model checking problem as it entails classifying each state s of a hybrid automaton as either positive or negative, depending on whether or not …
Extends PoS proof-of-stake transaction fee mechanism with miner utility model.
problem Designing a transaction fee mechanism for PoS protocol that incorporates miner utility.
method Introduced a new mechanism (BSP(θ)) incorporating a parameter θ to ensure user and miner incentives.
result The new mechanism (BSP(θ)) satisfies user and miner incentives and contract proofness.
The paper develops an asymptotic theory of self-supervised pre-training.
problem Sharpness of current rates in self-supervised pre-training and their accuracy.
method Two-stage M-estimation and tools from Riemannian geometry.
result Characterization of the limiting distribution of the downstream test risk.
pyLOT library simplifies machine learning on 3D point clouds via linearized optimal transport.
problem Performing machine learning tasks on 3D point clouds.
method Linearized optimal transport (LOT) to embed distributions into Hilbert space, enabling linear machine learning.
result Downstream tasks on embedded representations are simplified to linear operations.
Post-hoc uncertainty quantification improves on pre-trained neural networks without underfitting.
problem Uncertainty quantification in neural networks is underfitting or computationally demanding.
method Gaussian Process Activation function (GAPA) for neuron-level uncertainty, with two methods: GAPA-Free and GAPA-Variational.
result GAPA-Variational outperforms Laplace approximation on most datasets in uncertainty quantification metrics.
Optimus pre-trains sentences in a latent space for various NLP tasks.
problem Training large-scale language models for diverse NLP tasks.
method Pre-trained Variational Autoencoder (VAE) on large text corpus, fine-tuned for various tasks.
result Optimus achieves state-of-the-art on VAE language modeling benchmarks.
Theoretical study shows adversarial training improves robustness in deep learning models.
problem Ensuring robustness in pre-trained deep learning models.
method Theoretical analysis of adversarial training and feature purification in two-layer neural networks.
result Adversarial training leads to feature purification, making models more robust to attacks.
Model compression techniques on Deep Neural Network (DNN) have been widely acknowledged as an effective way to achieve acceleration on a variety of platforms, and DNN weight pruning is a straightforward and effective method. There are currently two mainstreams of pruning methods representing two extremes of pruning reg…
A RL-based method adds conditional controls to pre-trained diffusion models.
problem Precise control over generated samples in diffusion models.
method Formulates the task as an RL problem, using a classifier and KL divergence as reward functions.
result Produces soft-optimal policies that maximize reward functions, enabling conditional sampling.
Latent variable models for network data extract a summary of the relational structure underlying an observed network. The simplest possible models subdivide nodes of the network into clusters; the probability of a link between any two nodes then depends only on their cluster assignment. Currently available models can b…
New computational methods improve clustering of objects.
problem Clustering objects based on their joint occurrence in sets.
method Genetic algorithm with renumbering, local search, and simplified model.
result Improvements enhance computational performance of genetic algorithm.
Transformers learn to cluster Gaussian mixtures as well as the EM algorithm.
problem Learning guarantees of Transformers in multi-class clustering of Gaussian mixtures.
method Developed a theory connecting Transformer's Softmax Attention layers to the EM algorithm's workflow.
result Transformers achieve minimax optimal rate for clustering Gaussian mixtures with sufficient training samples and initialization.
ImageNet pre-training has been regarded as essential for training accurate object detectors for a long time. Recently, it has been shown that object detectors trained from randomly initialized weights can be on par with those fine-tuned from ImageNet pre-trained models. However, the effects of pre-training and the diff…
The study of hierarchy in networks of the human brain has been of significant interest among the researchers as numerous studies have pointed out towards a functional hierarchical organization of the human brain. This paper provides a novel method for the extraction of hierarchical connectivity components in the human …
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function. As opposed to supervised deep learning, this line of research is in its infancy, and how to design and optimize suitable l…
Study how actions affect perception in embodied agents using group theory.
problem Understanding how actions influence perception in autonomous agents.
method Mathematical formalism of group theory applied to sensory commutativity of action sequences.
result Introduced Sensory Commutativity Probability (SCP) to measure action effects on perception.
This paper advocates a novel framework for segmenting a dataset in a Riemannian manifold M into clusters lying around low-dimensional submanifolds of M. Important examples of M, for which the proposed clustering algorithm is computationally efficient, are the sphere, the set of positive definite matrices, and the…
This paper simplifies conditional Sobol' indices calculation using PCE bases.
problem Computational inefficiency and lack of consistency in evaluating conditional Sobol' indices.
method Analytical extraction of conditional Sobol' indices via basis decomposition of PCE expansions.
result Derives closed-form expressions for conditional Sobol' indices.
DPTA improves CIL by adapting PTMs with dual prototypes.
problem Catastrophic forgetting in incremental learning with pre-trained models.
method Dual-Prototype Network with Task-wise Adaptation (DPTA).
result DPTA consistently outperforms recent methods by 1\%-5\% on multiple benchmarks.
Language models learn automotive complaints, improving defect detection.
problem Detecting technical quality issues in customer feedback.
method Continual pre-training on ODI Complaints data set.
result Models achieve high precision in identifying technical terms.