Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we p…
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Data-Independent”
Data-independent pruning method reduces neural network size with accuracy guarantees.
problem Limited computational and memory resources for neural networks.
method Structured pruning using coresets.
result First efficient algorithm with worst-case guarantees on compression and accuracy.
Hybrid clustering combines partitional and hierarchical clustering for computational effectiveness and versatility in cluster shape. In such clustering, a dissimilarity measure plays a crucial role in the hierarchical merging. The dissimilarity measure has great impact on the final clustering, and data-independent prop…
EdgeAI aims to deploy deep learning on IoT devices.
problem Deep learning's high computational demands on IoT devices.
method Addressing data-independent deployment and communication-aware distributed inference.
result New directions to enable deep learning on IoT devices.
Previous work showed empirically that large neural networks can be significantly reduced in size while preserving their accuracy. Model compression became a central research topic, as it is crucial for deployment of neural networks on devices with limited computational and memory resources. The majority of the compress…
An Efficient Calibration Framework for Volatility Derivatives under Rough Volatility with Jumpsq-fin.CP
A fast calibration method for rough volatility models with jumps.
problem Calibrating stochastic volatility models to market data efficiently.
method Structure-preserving approach: split pricing formula, precompute data-independent integrals, and approximate market-dependent remainder with neural networks.
result Calibration achieves high accuracy and speed, and a pure-jump rough volatility model adequately captures VIX dynamics.
The group membership prediction (GMP) problem involves predicting whether or not a collection of instances share a certain semantic property. For instance, in kinship verification given a collection of images, the goal is to predict whether or not they share a {\it familial} relationship. In this context we propose a n…
Paper introduces data-dependent SSP for private linear and logistic regression.
problem Private linear and logistic regression with better performance.
method Data-dependent sufficient statistic perturbation (SSP) for linear and logistic regression.
result Data-dependent SSP outperforms state-of-the-art methods for linear and logistic regression.
Study identifies and validates a method for system identification of Markov jump linear systems.
problem System identification for autonomous Markov jump linear systems with complete state observations.
method Proposes switched least squares method for identification and derives rates of convergence.
result Data-independent rate of convergence is , showing strong consistency.
We propose a simple, tractable lower bound on the mutual information contained in the joint generative density of any latent variable generative model: the GILBO (Generative Information Lower BOund). It offers a data-independent measure of the complexity of the learned latent variable description, giving the log of the…
Squint bound improved by removing term.
problem Improving the Squint bound by removing the term.
method Using the Krichevsky--Trofimov algorithm to change the prior.
result Removed the term from the Squint bound.
In this work we investigate the reasons why Batch Normalization (BN) improves the generalization performance of deep networks. We argue that one major reason, distinguishing it from data-independent normalization methods, is randomness of batch statistics. This randomness appears in the parameters rather than in activa…
EmbraceNet fusion model for multi-sensor activity recognition.
problem Human activity recognition using multiple sensors is challenging.
method Independent processing of each sensor, feature fusion with EmbraceNet, post-processing, and additional processes.
result Improved performance in SHL recognition challenge.
Fisher GANcs.LG
Generative Adversarial Networks (GANs) are powerful models for learning complex distributions. Stable training of GANs has been addressed in many recent works which explore different metrics between distributions. In this paper we introduce Fisher GAN which fits within the Integral Probability Metrics (IPM) framework f…
A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream tasks, there is little empirical evidence that supports this claim. In this paper, …
The paper studies a stochastic majority vote approach to improve classifier accuracy.
problem Improving classifier accuracy over ensembles of classifiers.
method Minimizing a PAC-Bayes generalization bound with Dirichlet distributions.
result Achieves state-of-the-art accuracy and tight generalization bounds.
Study compares LRMC algorithms under dependent sampling in various applications.
problem Recovering missing entries in partially observed low-rank matrices with dependent sampling.
method Various LRMC algorithms tested under dependent sampling in different contexts.
result Performance differences among LRMC algorithms under dependent sampling.
Researchers estimate optimal PAC-Bayes bounds using Hamiltonian Monte Carlo.
problem Estimating tight PAC-Bayes bounds with restricted posterior families.
method Sampling from optimal Gibbs posterior using Hamiltonian Monte Carlo, estimating KL divergence, and proposing high-probability bounds.
result Significant tightness gaps in PAC-Bayes bounds, up to 5-6% in some cases.
No bad local minima: Data independent training error guarantees for multilayer neural networksstat.ML
We use smoothed analysis techniques to provide guarantees on the training loss of Multilayer Neural Networks (MNNs) at differentiable local minima. Specifically, we examine MNNs with piecewise linear activation functions, quadratic loss and a single output, under mild over-parametrization. We prove that for a MNN with …
The Gibbs algorithm's generalization error is bounded, improving with prior volume in low temperatures.
problem Bounding the generalization error of the Gibbs algorithm in low temperature regimes.
method Analyzes the Gibbs algorithm's performance, extending known high-temperature bounds to low-temperature scenarios.
result With high probability, the generalization error decreases with the total prior volume of similar hypotheses.
The paper addresses challenges in edge deep learning for IoT, proposing new directions.
problem Challenges in large-scale deep learning adoption for IoT devices.
method Unified view targeting three research directions: federated learning, data-independent deployment, and communication-aware inference.
result A network-centric approach is needed for edge intelligence.
Directed graphical models (DGMs) are a class of probabilistic models that are widely used for predictive analysis in sensitive domains, such as medical diagnostics. In this paper we present an algorithm for differentially private learning of the parameters of a DGM with a publicly known graph structure over fully obser…
The paper improves deep learning generalization bounds using PAC-Bayes compression.
problem Improving generalization bounds for deep neural networks.
method Quantizing neural network parameters in a linear subspace to develop tight generalization bounds.
result Large models can be compressed significantly, explaining Occam's razor.
Superposition accelerates training to a universal power-law exponent.
problem Training dynamics in neural networks.
method Teacher-student framework and analytic theory.
result Superposition leads to a universal power-law exponent of ~1, independent of data and channel statistics.
We propose a new class of data-independent locality-sensitive hashing (LSH) algorithms based on the fruit fly olfactory circuit. The fundamental difference of this approach is that, instead of assigning hashes as dense points in a low dimensional space, hashes are assigned in a high dimensional space, which enhances th…
New research shows many batch selection methods for training work just as well as full batch training.
problem Finding optimal batch selection methods for training.
method Analysis of mini-batch Gradient Descent (GD) and Stochastic GD (SGD) with various batch selection rules.
result All mini-batch schedules, including deterministic ones, generalize optimally for smooth Lipschitz-convex/nonconvex/strongly-convex loss functions.
Patch augmentation boosts neural network accuracy and robustness.
problem Improving neural network accuracy and robustness to adversarial attacks.
method Data augmentation technique creating new images by superimposing patches from image pairs.
result Significant accuracy improvements on CIFAR-10 and CIFAR-100 datasets.
This paper introduces hyperspherical prototype networks, which unify classification and regression with prototypes on hyperspherical output spaces. For classification, a common approach is to define prototypes as the mean output vector over training examples per class. Here, we propose to use hyperspheres as output spa…
Stochastic configuration networks (SCNs) as a class of randomized learner model have been successfully employed in data analytics due to its universal approximation capability and fast modelling property. The technical essence lies in stochastically configuring hidden nodes (or basis functions) based on a supervisory m…
A new method tests independence for causal discovery on discrete data.
problem Inferring causal directions on discrete and categorical data.
method Subsampling-based method to test independence between cause and mechanism.
result Our method works for both discrete and categorical data without functional model assumptions.
One of the biggest issues in deep learning theory is the generalization ability of networks with huge model size. The classical learning theory suggests that overparameterized models cause overfitting. However, practically used large deep models avoid overfitting, which is not well explained by the classical approaches…
New KD-tree based method for private synthetic data generation.
problem Creating private synthetic data that accurately represents real data.
method KD-trees combined with noise perturbation for differentially private synthetic data generation.
result Our data-dependent approach improves utility over prior work and scales well.
Deep learning autoencoder detects bee colony anomalies.
problem Early detection of bee swarms and other unusual behaviors.
method Deep Recurrent Autoencoder model trained on sensor data.
result Autoencoder detects anomalies independent of their origin.
Study learns linear system dynamics from noisy bilinear data.
problem Learning linear dynamics from bilinear observations with process and measurement noise.
method Regression with Kronecker product design, data-dependent and independent error bounds.
result Upper bounds on statistical error rates and sample complexity for learning dynamics matrices.
Regularization preserves topological data structure in autoencoders.
problem Ensuring topological data structure preservation in autoencoders.
method Regularization using Legendre nodes to preserve manifold embedding.
result Regularized autoencoders ensure one-to-one embedding of data manifolds.
This paper shows neural networks can learn non-linear sparse parities.
problem The challenge of learning non-linear models with neural networks.
method Gradient descent on depth-two neural networks.
result Sparse parities are learnable by neural networks but not by linear methods.
Assessing and improving reliability of neighbor embedding methods: a map-continuity perspectivestat.ME
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
Study confirms rough volatility in financial data, independent of microstructure noise.
problem Characterizing volatility in financial markets, especially rough volatility.
method Used range-based volatility estimators to confirm findings from fractional behavior.
result Log-volatility behaves like fractional Brownian motion with an even lower Hurst exponent.
Algorithms typically come with tunable parameters that have a considerable impact on the computational resources they consume. Too often, practitioners must hand-tune the parameters, a tedious and error-prone task. A recent line of research provides algorithms that return nearly-optimal parameters from within a finite …
Unified framework for deriving generalization bounds in supervised learning.
problem Generalization error bounds in supervised learning.
method Data Processing Inequality PAC-Bayesian framework.
result Unified bounds on binary Kullback-Leibler generalization gap for various divergences.
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalizationstat.ML
Near-interpolating models grow norms quickly, affecting generalization.
problem Understanding the trade-off between interpolation and generalization in near-interpolating models.
method Random matrix theory and eigendecay analysis of data covariance matrix.
result Near-interpolating models exhibit rapid norm growth and worse generalization trade-offs.
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- Internal Covariate Shift-- the current solution has certain drawbacks. Specifically, BN depends on batch statistics for layerwise input normalization during training which makes the estimates of …
While the authors of Batch Normalization (BN) identify and address an important problem involved in training deep networks-- \textit{Internal Covariate Shift}-- the current solution has certain drawbacks. For instance, BN depends on batch statistics for layerwise input normalization during training which makes the esti…
Sharp analysis of power iteration for tensor PCA, improving convergence and stopping criteria.
problem Analyzing the power iteration algorithm for tensor PCA to improve convergence and stopping criteria.
method Sharp bounds on the number of iterations, revealing a smaller algorithmic threshold, proposing a stopping criterion.
result Sharp bounds on the number of iterations required for power method to converge, revealing a smaller algorithmic threshold than previously conjectured.
A new method for binary ICA using non-stationary sources.
problem Independent component analysis of binary data.
method Linear mixing model in latent space, followed by binary observation model with non-stationary sources.
result Proves non-identifiability with few observed variables but identifies with more variables.
We present a novel notion of complexity that interpolates between and generalizes some classic existing complexity notions in learning theory: for estimators like empirical risk minimization (ERM) with arbitrary bounded losses, it is upper bounded in terms of data-independent Rademacher complexity; for generalized Baye…
New test detects independence in streaming data, adapting to data complexity.
problem Independence testing in streaming data with adaptive stopping.
method Sequential kernelized independence tests using betting principles.
result Valid inference in streaming data with improved power.
This work surveys attacks and defenses on edge neural networks.
problem Security challenges of edge neural networks due to their compute and memory intensity, data-independence, and privacy risks.
method Taxonomy of attacks and defenses on edge-deployed neural networks.
result New security considerations and approaches are needed for edge DNNs.