Bayesian feature allocation models are a popular tool for modelling data with a combinatorial latent structure. Exact inference in these models is generally intractable and so practitioners typically apply Markov Chain Monte Carlo (MCMC) methods for posterior inference. The most widely used MCMC strategies rely on an e…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “feature updates”
Develops efficient method for updating models with small data changes.
problem Efficiently updating models when data changes (e.g., adding/removing instances/features).
method Generalized Low-Rank Update (GLRU) for non-linear estimators.
result Provides updated solutions with computational complexity proportional to dataset changes.
New method controls sparse feature updates in deep networks.
problem Understanding sparse feature updates in deep networks during training.
method Iterative linearised training method to control sparse feature updates.
result Iterative linearised training surprisingly performs on par with standard training, requiring less frequent feature learning.
New insights into neural network feature learning through multi-step gradient descent.
problem Understanding feature learning in two-layer neural networks with limited width.
method Characterization of feature learning through two steps of gradient descent with specific step sizes.
result The second step of gradient descent reveals multiple learned directions, not limited to a single direction as in the first step.
New learning rule simplifies Bayesian updates for deep learning.
problem Bayesian learning rule's complexity and manifold constraints.
method Lie-group approach to simplify Bayesian updates.
result New algorithm learns sparse features in deep learning.
FedCONST adapts update magnitudes to enhance feature generalization in FL.
problem Heterogeneous client data in FL leads to overfitting and distorted transferable features.
method FedCONST uses linear convex constraints to stabilize training and preserve generalization.
result FedCONST enhances feature transferability and robustness, achieving state-of-the-art performance.
Communication through e-mails remains to be highly formalized, conventional and indispensable method for the exchange of information over the Internet. An ever-increasing ratio and adversary nature of spam e-mails have posed a great many challenges such as uneven class distribution, unequal error cost, frequent change …
NeSGD efficiently updates tensor-based features for online model learning in multi-way data.
problem Incremental updates of tensor-based features and model coefficients for evolving data distributions.
method Online NeSGD for CP decomposition of tensor data.
result Proposed NeSGD method significantly improves classification accuracy and adapts to changing data distributions.
Proposes a method to update model weights by dynamically changing features during training.
problem Updating model weights efficiently during training.
method Dynamic feature replacement during training to update model weights.
result Increased model accuracy with same training time and complexity.
New framework provides privacy guarantees for practical federated learning.
problem Inadequate privacy guarantees for federated learning due to restrictive assumptions.
method Fed--NormEC, integrating multiple local updates, partial client participation, and standard assumptions.
result Provably convergent and differentially private federated learning framework.
Non-negative matrix factorization is a popular tool for decomposing data into feature and weight matrices under non-negativity constraints. It enjoys practical success but is poorly understood theoretically. This paper proposes an algorithm that alternates between decoding the weights and updating the features, and sho…
This paper shows how deep neural networks can learn rich, independent features that significantly deviate from initialization.
problem Understanding how deep neural networks achieve meaningful feature learning and global convergence.
method Investigation of infinitely wide, -layer neural networks using the tensor program framework under Maximal Update parametrization.
result SGD enables these networks to learn linearly independent features that substantially deviate from their initial values, capturing relevant data information.
Paper proves multiplicative weight updates can train neural networks without learning rate tuning.
problem Vanishing and exploding gradients in gradient descent for compositional functions.
method Proves descent lemma for compositional functions using multiplicative weight updates and derives Madam optimizer.
result Madam optimizer trains state-of-the-art neural networks without learning rate tuning.
Unified NMF models for various noise distributions, improving feature extraction.
problem Inadequate assumptions for NMF under complex data distributions.
method Unified framework using MM-algorithms for traditional and convex NMF under Tweedie and Negative Binomial models.
result Unified multiplicative update rules for all models, including novel updates for convex NMF.
Two algorithms address limited adaptivity in generalized linear contextual bandits.
problem Limited adaptivity in generalized linear contextual bandits.
method Two algorithms, B-GLinCB and RS-GLinCB, designed for two settings of limited adaptivity.
result Achieved regret in both settings.
New framework reduces strategic manipulation cost for minority groups in fair classification.
problem Strategic manipulation disparities in fair classification.
method Constrained optimization framework that constructs classifiers to reduce strategic manipulation cost for minority groups.
result Empirically, the approach reduces strategic manipulation cost for minority groups over multiple real-world datasets.
A novel Bayesian computation method using importance weighting improves numerical stability and performance.
problem Bayesian computation stability and performance issues.
method Nonparametric approach via feature means, importance weighting, and kernel Bayes' rule.
result Importance weighted kernel Bayes' rule yields superior numerical stability and performance.
GENIE balances domain-invariant feature learning and gradient alignment for improved DG performance.
problem Domain Generalization (DG) overfitting to domain-specific features
method GENIE (Generalization-ENhancing Iterative Equalizer) optimizer
result Prevents a small subset of parameters from dominating optimization, promoting domain-invariant feature learning
We extend our studies of a quantum field model defined on a lattice having the dilation group as a local gauge symmetry. The model is relevant in the cross-disciplinary area of econophysics. A corresponding proposal by Ilinski aimed at gauge modeling in non-equilibrium pricing is realized as a numerical simulation of t…
Contrastive regularization improves semi-supervised learning by better propagating confident pseudo-labels.
problem Consistency regularization's limitation in high performance and efficiency.
method Proposes contrastive regularization to update model features, pushing confident labels into unlabeled samples.
result Improves semi-supervised learning tasks with fewer training iterations and robust performance.
We present safe active incremental feature selection~(SAIF) to scale up the computation of LASSO solutions. SAIF does not require a solution from a heavier penalty parameter as in sequential screening or updating the full model for each iteration as in dynamic screening. Different from these existing screening methods,…
This work analyzes how neural networks learn representations in actor-critic algorithms.
problem Theoretical support for neural AC algorithms is limited to linear function approximations.
method Mean-field analysis of a two-timescale learning AC algorithm with overparameterized networks.
result Neural AC finds the globally optimal policy at a sublinear rate in the continuous-time and infinite-width limiting regime.
A new method for machine learning updates reduces complexity and improves robustness.
problem Stochastic gradient updates are inefficient and sensitive to feature scaling.
method Incremental Gauss-Newton Descent (IGND) reduces the need for matrix operations and improves robustness.
result IGND improves robustness to sensitivity scaling and can be competitive with common stochastic optimizers.
Inverse classification, the process of making meaningful perturbations to a test point such that it is more likely to have a desired classification, has previously been addressed using data from a single static point in time. Such an approach yields inflated probability estimates, stemming from an implicitly made assum…
A major goal of unsupervised learning is to discover data representations that are useful for subsequent tasks, without access to supervised labels during training. Typically, this involves minimizing a surrogate objective, such as the negative log likelihood of a generative model, with the hope that representations us…
Framework explains how dual deep networks learn features from unlabeled data.
problem Understanding self-supervised learning with dual deep networks.
method Theoretical framework and hierarchical latent tree model.
result Deep ReLU networks learn latent variables through contrastive SSL.
In this paper, we propose a test, called Flagged-1-Bit (F1B) test, to study the intrinsic capability of recurrent neural networks in sequence learning. Four different recurrent network models are studied both analytically and experimentally using this test. Our results suggest that in general there exists a conflict be…
We introduce novel variants of momentum by incorporating the variance of the stochastic loss function. The variance characterizes the confidence or uncertainty of the local features of the averaged loss surface across the i.i.d. subsets of the training data defined by the mini-batches. We show two applications of the g…
In the past decades, spectral clustering (SC) has become one of the most effective clustering algorithms. However, most previous studies focus on spectral clustering tasks with a fixed task set, which cannot incorporate with a new spectral clustering task without accessing to previously learned tasks. In this paper, we…
BOIL updates model body only, showing better few-shot learning performance.
problem Few-shot learning efficiency with model reuse vs. change.
method Proposes BOIL, updating only model body, freezing head.
result Significantly outperforms MAML on cross-domain tasks.
FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcs.LG
Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized. This framework faces several systems-oriented challenges which include (i) communication bottleneck since a large number of devices upload their local updates to a parameter server, a…
FedShuffle improves local updates in FL, especially with data imbalance.
problem Data imbalance in FL leads to different clients performing different numbers of local updates.
method FedShuffle incorporates random reshuffling, data imbalance, and client sampling.
result FedShuffle improves upon FL methods that assume homogeneous updates in heterogeneous setups.
Deep reinforcement learning (DRL) methods such as the Deep Q-Network (DQN) have achieved state-of-the-art results in a variety of challenging, high-dimensional domains. This success is mainly attributed to the power of deep neural networks to learn rich domain representations for approximating the value function or pol…
Feature matters for salient object detection. Existing methods mainly focus on designing a sophisticated structure to incorporate multi-level features and filter out cluttered features. We present Progressive Feature Polishing Network (PFPN), a simple yet effective framework to progressively polish the multi-level feat…
Adaptive XGBoost improves accuracy on evolving data streams by updating the ensemble dynamically.
problem Concept drift in evolving data streams.
method Adapts XGB to update the ensemble with new data, maintaining consistency with current concept.
result Improves classification accuracy on evolving data streams compared to other methods.
COLoKe adapts Koopman embeddings online, reducing overfitting and improving long-term predictions.
problem Online adaptation of Koopman embeddings to avoid overfitting and maintain long-term predictive accuracy.
method Combines deep feature learning with multistep prediction consistency in a lifted space, using a conformal-style mechanism for selective updates.
result Empirically effective in reducing overfitting and maintaining long-term predictive accuracy.
This paper introduces a family of local feature aggregation functions and a novel method to estimate their parameters, such that they generate optimal representations for classification (or any task that can be expressed as a cost function minimization problem). To achieve that, we compose the local feature aggregation…
In this paper, we propose a dictionary update method for Nonnegative Matrix Factorization (NMF) with high dimensional data in a spectral conversion (SC) task. Voice conversion has been widely studied due to its potential applications such as personalized speech synthesis and speech enhancement. Exemplar-based NMF (ENMF…
Dual training method for EBMs with overparametrized neural networks.
problem Training EBMs with non-convex energies is challenging.
method Derive variational principles and dual GDA algorithm for feature-learning regime.
result Dual GDA algorithm performs best with similar time scales for features and particles.
At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase. However, real-world problem is far more challenging because: i) new classes unseen in the training phase can appear when predicting; ii) discriminative features need to evolve when…
RIFLE improves deep transfer learning by reinitializing fully-connected layers.
problem Limited improvement in transfer learning accuracy with pre-trained models on small datasets.
method Re-Initializing fully-connected layers with random scratch during fine-tuning.
result Significant improvement in deep transfer learning accuracy across various datasets.
Breaking symmetry in training data is key for generalization in feature learning kernels.
problem Grokking in algebraic tasks, where models perform well on training but fail on unseen data.
method Used Recursive Feature Machine (RFM) with AGOP to learn task-relevant features, breaking symmetry in training data.
result Generalization occurs only when symmetry in the training set is broken, and RFM generalizes by recovering underlying invariance group action.
There are time series that are amenable to recurrent neural network (RNN) solutions when treated as sequences, but some series, e.g. asynchronous time series, provide a richer variation of feature types than current RNN cells take into account. In order to address such situations, we introduce a unified RNN that handle…
Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain knowledge. More recently, the trend is to learn these representations through stochasti…
Transformers predict price movements from limit order books.
problem Predicting price movements from limit order books.
method Causal convolutional network with masked self-attention.
result Significantly outperforms existing architectures on FI-2010 dataset.
IAL uses interactive learning to improve model performance with minimal human feedback.
problem Overfitting and high human interaction cost in training neural networks.
method IAL framework with NAP attention generator and reranking algorithm.
result IAL significantly outperforms baselines with less retraining and human interaction.
Distributed representations of sentences have become ubiquitous in natural language processing tasks. In this paper, we consider a continual learning scenario for sentence representations: Given a sequence of corpora, we aim to optimize the sentence encoder with respect to the new corpus while maintaining its accuracy …
Fast feature selection for SHM using canonical correlation.
problem Feature selection for structural health monitoring.
method Greedy search of sum of squared canonical correlation coefficients.
result Extremely fast feature selection with good performance.