Generalizes PCA and ICA for continuous-time signals using neural networks.
problem Low-rank decomposition of continuous-time vector-valued signals.
method Implicit neural network framework to learn numerical approximations of PCA and ICA.
result Unified approach to PCA and ICA in continuous domain, enforcing decorrelation and independence.
A tuning-free method recovers jointly sparse signals in MMV using implicit regularization.
problem Recovering jointly sparse signals in MMV with minimal tuning or prior knowledge.
method Reparameterizes MMV estimation matrix into decoupled factors and applies gradient descent to a least-squares objective.
result Gradient descent dynamics exhibit a momentum-like effect, converging towards an idealized row-sparse solution.
This work aims to separate buying preferences from merchandise commercials in fashion e-retail.
problem Difficult to infer customer preference from sales data due to implicit signals.
method Extends earlier work on explicit signals to implicit signals from user behavior.
result Derives a metric to separate buying preferences from merchandise commercials.
Gradient matching method estimates implicit regularization in complex deep learning systems.
problem Estimating implicit regularization in modern deep learning systems with complex modifications.
method Gradient matching methods to empirically estimate implicit regularization.
result Empirical estimation of implicit regularization in arbitrary networks, including dropout.
FreSh shifts model's initial frequency spectrum to match target signal, improving neural representation performance.
problem MLPs' low-frequency bias limits capturing high-frequency details accurately.
method FreSh selects embedding hyperparameters to align model's initial output spectrum with target signal's spectrum.
result FreSh improves performance across various neural representation methods and tasks with minimal computational overhead.
Theory explains generalization in deep learning, reducing memorization and improving performance.
problem Understanding and improving generalization in deep learning models.
method Developed a non-asymptotic theory using the empirical neural tangent kernel.
result Generalization is possible even when the kernel evolves significantly, with coherent signal accumulation and noise suppression.
New method uses deep learning to solve linear inverse problems.
problem Solving linear inverse problems with high-dimensional signals.
method Stochastic coarse-to-fine gradient ascent procedure using implicit prior from denoising CNN.
result General algorithm for solving linear inverse problems without additional training.
Market makers optimize trading with a new implicit scheme for complex inequalities.
problem Optimizing trading in a limit order book with stochastic and impulse control.
method Implicit numerical scheme coupled with policy iteration algorithm.
result Convergence to the unique viscosity solution of the HJBQVI.
Neural network detects spectrum signals under uncertain parameters.
problem Spectrum sensing under uncertain primary user signal parameters.
method Trained neural network to detect modulated signals robustly.
result Neural network gains robustness under carrier frequency, phase, and symbol time offsets.
New system uses wearable bio-signals for easy authentication.
problem Security of private information on wearables is a concern.
method Context-dependent soft-biometric authentication using heart rate, gait, and breathing audio.
result Binary SVM with RBF kernel achieves high accuracy and low EER.
Gradient descent with specific initialization and step size achieves optimal sparse signal recovery.
problem Reconstructing a sparse signal from underdetermined linear measurements.
method Gradient descent with specific initialization, step size, and stopping time.
result Achieves the minimax rate with poly-logarithmic factors and adapts to instance difficulty.
Presentation bias is one of the key challenges when learning from implicit feedback in search engines, as it confounds the relevance signal with uninformative signals due to position in the ranking, saliency, and other presentation factors. While it was recently shown how counterfactual learning-to-rank (LTR) approache…
RLVR learning dynamics naturally create an implicit curriculum for transformers.
problem How rewards based on final outcomes help overcome the long-horizon barrier in reasoning models.
method Developed a theory of training dynamics for RLVR on transformers, using Fourier analysis on finite groups.
result Mixed-difficulty training induces an implicit curriculum that shapes the learning progression from easy to hard.
'Sharing of statistical strength' is a phrase often employed in machine learning and signal processing. In sensor networks, for example, missing signals from certain sensors may be predicted by exploiting their correlation with observed signals acquired from other sensors. For humans, our hands move synchronously with …
New method implicitly regularizes high-dimensional linear regression using gradient descent.
problem Sparse vector estimation in high-dimensional linear regression.
method Gradient descent on residual sum of squares with early stopping under overparameterization.
result Gradient descent implicitly leads to nearly sparse optimal solutions without explicit penalties.
Kernel-guided training stabilizes GANs by controlling discrepancies.
problem Stability and interpretability issues in GANs.
method Kernel-based regularization to control discrepancies in GAN loss function.
result Theoretical guarantees on stability of the training dynamics.
Kernel-guided training stabilizes GANs by controlling discrepancies.
problem Stability and interpretability issues in GANs.
method Kernel-based regularization to control discrepancies in GAN loss function.
result Theoretical guarantees on stability of the training dynamics.
Study proposes a time-aware model to predict user conversion intent.
problem Weak predictive signals from users not suitable for conversion prediction.
method Time-aware approach to model user activities and capture conversion intent signals.
result Approach outperforms other models on real-world datasets.
Improved IVIM imaging accuracy with neural networks and uncertainty estimation.
problem Low accuracy in IVIM imaging due to SNR and motion artifacts.
method Implicit IVIM signal acquisition model using neural networks for full posterior distribution.
result Improved parameter estimation accuracy by 65% on synthetic data.
GD with large init shows incremental learning in matrix factorization.
problem Understanding GD's behavior with large initial values in matrix factorization.
method Signal-to-noise ratio concepts and inductive arguments.
result Uncovering an incremental learning phenomenon in GD with large initialization.
The paper studies implicit regularization in over-parameterized models for high-dimensional data.
problem Understanding implicit regularization in over-parameterized models for high-dimensional data.
method The paper designs regularization-free algorithms for the high-dimensional single index model and provides theoretical guarantees for the induced implicit regularization phenomenon.
result The proposed methods achieve minimax optimal statistical rates of convergence and outperform classical methods with explicit regularization.
A new framework enhances binaural audio for moving talkers.
problem Real-time binaural audio enhancement for moving sound sources.
method Mixture-of-experts framework combining multiple binaural filters.
result Dynamic spatial audio rendering adapts to moving talkers.
RLVR training dynamics reveal an implicit curriculum that shapes learning progression.
problem Understanding how RLVR overcomes the long-horizon barrier.
method Developed a theory of training dynamics for RLVR on transformers, using Fourier analysis on finite groups.
result Mixed-difficulty training naturally follows an implicit curriculum, shaping the learning progression from easy to hard.
CNNs show sensitivity to low-frequency signals due to image frequency distribution.
problem Understanding why CNNs are sensitive to low-frequency signals.
method Theoretical analysis of CNN representations in frequency space.
result CNNs sensitivity to low-frequency signals is due to the frequency distribution of natural images.
The bane of one-class collaborative filtering is interpreting and modelling the latent signal from the missing class. In this paper we present a novel Bayesian generative model for implicit collaborative filtering. It forms a core component of the Xbox Live architecture, and unlike previous approaches, delineates the o…
DDMI generates high-quality INRs by adapting positional embeddings.
problem Existing INR generative models fail to produce high-quality representations.
method DDMI uses adaptive positional embeddings and a D2C-VAE to enhance expressive power.
result DDMI outperforms existing models across multiple modalities and datasets.
Deep learning model improves personalized product recommendations.
problem Large-scale personalized recommendation systems with implicit feedback.
method Combines neural attention mechanisms and representation learning for efficient, high-coverage models.
result Significant performance improvements over alternative methods in offline and online settings.
A new method optimizes recommender systems by addressing missing-not-at-random implicit feedback.
problem Missing-not-at-random implicit feedback in recommender systems.
method Defining an ideal loss function and proposing an unbiased estimator to optimize relevance.
result The proposed method improves performance, especially for rare items.
RINS-T solves time series inverse problems robustly without pretraining.
problem Recovering original signals from corrupted time series data.
method Implicit neural solvers with robust optimization techniques.
result RINS-T achieves high recovery performance without pretraining.
Deep neural networks implicitly self-regularize, shown by random matrix theory.
problem Understanding and quantifying implicit self-regularization in deep neural networks.
method Random Matrix Theory applied to various DNNs, including pre-trained and self-trained models.
result DNN training implicitly implements self-regularization, observable in empirical spectral densities.
New method for optimizing neural networks with quantized weights and activations.
problem Improving resource efficiency of deep neural networks.
method Mean-field theory applied to quantized activation networks.
result Closed-form equation for maximal trainable depth, showing Lmax∝N1.82. We devise a USDCHF trading strategy using the dynamics of gold as a filter. Our strategy involves modelling both USDCHF and gold using a coupled hidden Markov model (CHMM). The observations will be indicators, RSI and CCI, which will be used as triggers for our trading signals. Upon decoding the model in each iteration…
Unified analysis of neural networks for sparse signal recovery.
problem Sparse signal recovery from few linear measurements.
method Introduces a general class of neural networks with weight-sharing, analyzes their Rademacher complexity, and derives generalization bounds.
result Derives generalization bounds that depend linearly on the number of parameters and depth, applicable to various neural network types.
New method infers human sensorimotor costs from behavior.
problem Inferring human sensorimotor costs from observed behavior.
method Inverse optimal control with signal-dependent noise.
result Recovering costs and benefits in sensorimotor behavior.
Logit regularization induces logit clustering, affecting classifier performance.
problem Understanding the mechanism of logit regularization in classification.
method Analysis of logit regularization in linear classification, proving logit clustering leads to Fisher's Linear Discriminant alignment.
result Logit regularization can halve critical sample complexity and induce robust generalization.
New model for recovering unverifiable signals from observers in decentralized networks.
problem Verifying the level of service provided by untrusted parties in decentralized networks.
method Formal model of signal elicitation, source identifiability condition, and peer prediction techniques.
result Existence of a strictly truthful mechanism for unverifiable signal recovery.
RMT reveals self-regularization in neural networks, including traditional and heavy-tailed forms.
problem Understanding and quantifying self-regularization in neural networks.
method Application of Random Matrix Theory to analyze weight matrices of various neural network models.
result Identification of 5+1 phases of training in neural networks, including traditional and heavy-tailed self-regularization.
Self-training in linear models shows a U-shaped test-risk curve due to signal forgetting and denoising.
problem Understanding the dynamics of iterative self-training in high-dimensional linear regression.
method Derivation of deterministic-equivalent recursions for prediction risk and effective noise, analysis of signal forgetting and denoising effects.
result An optimal early-stopping time is determined, and a U-shaped test-risk curve is observed.
This paper improves the scalability of sparse neural network compression.
problem Sparse neural network compression for diverse data modalities.
method State-of-the-art sparsification techniques and meta-learning.
result Meta-learning sparse compression networks achieve new state-of-the-art results.
Study finds macroeconomic indicators predict health workforce and infrastructure measures.
problem Evaluating the predictive value of macroeconomic indicators for public health targets.
method Examined multiple forecasting approaches including neural networks, generalized additive models, random forests, and time series models with exogenous indicators.
result Macroeconomic indicators provide consistent and reproducible predictive signals for health workforce and infrastructure measures, but less so for other targets.
This paper shows how to train only the implicit layer of overparameterized implicit neural networks.
problem Understanding how the implicit layer contributes to the training of overparameterized implicit neural networks.
method Restricting training to only the implicit layer and analyzing the generalization error for ReLU-activated networks.
result Global convergence is guaranteed even if only the implicit layer is trained, and gradient flow with proper random initialization can achieve small generalization errors.
Paper studies the theoretical equivalence between implicit and explicit neural networks in high dimensions.
problem Lack of theoretical analysis of implicit and explicit neural networks.
method Examined high-dimensional implicit neural networks and established their equivalence to explicit networks.
result Equivalence between implicit and explicit neural networks in high dimensions.
Continuous semi-implicit models enable faster training and better performance in generative modeling.
problem Slow convergence in hierarchical semi-implicit models during training.
method CoSIM, a continuous semi-implicit model that incorporates a continuous transition kernel for efficient training.
result CoSIM achieves superior performance on image generation tasks compared to existing methods.
Gradient descent converges to a global minimum in nonlinear ReLU implicit networks with linear width.
problem Understanding convergence of gradient methods in nonlinear, infinitely deep ReLU networks.
method Introduced a scaling constant to ensure well-posedness of the equilibrium equation, proving convergence to a global minimum for linear width networks.
result Gradient descent converges to a global minimum at a linear rate for nonlinear ReLU implicit networks with linear width.
DSIVI improves variational autoencoders by optimizing a proper lower bound on ELBO.
problem Improving variational autoencoders with implicit priors.
method Introducing DSIVI, a method that optimizes a proper lower bound on ELBO for models with semi-implicit priors and posteriors.
result DSIVI improves the performance of VampPrior, a state-of-the-art prior for variational autoencoders.
Study finds implicit government guarantee improves municipal investment bond ratings.
problem Questioning the objectivity of municipal investment bond ratings due to implicit government guarantee.
method Text mining of policy documents and PMC index model for implicit guarantee strength calculation.
result Implicit government guarantee boosts municipal investment bond ratings, especially in less developed regions.
Study shows SGD's generalization is not explained by implicit bias.
problem Explaining the generalization ability of overparameterized learning algorithms.
method Revisited Stochastic Convex Optimization with SGD, demonstrating limitations of implicit bias.
result No distribution-independent or distribution-dependent implicit regularizer can explain SGD's generalization.
This paper measures the intensity of implicit government guarantees using PMC index model.
problem Excessive local government debt due to implicit government guarantees.
method Text mining of policy documents related to municipal investment bonds, PMC index model.
result Recent policies have reduced the intensity of implicit government guarantees.