In this paper, we theoretically prove that adding one special neuron per output unit eliminates all suboptimal local minima of any deep neural network, for multi-class classification, binary classification, and regression with an arbitrary loss function, under practical assumptions. At every local minimum of any deep n…
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.
168,786 papers · 148 categories
Trend · papers per month
48 results for “parameter elimination”
Improved particle Gibbs sampling by marginalizing parameters.
problem Bayesian inference in high-dimensional state-space models is challenging.
method Marginalized particle Gibbs sampling, combining MCMC and sequential Monte Carlo.
result Marginalization improves performance beyond the Gibbs sampler, scaling linearly.
An algorithm learns from multiple models to match an oracle's risk.
problem Learning from multiple noisy models to estimate a target parameter.
method Elimination rounds algorithm for adaptive learning.
result Risk of weak-oracle learner matches that of an oracle in multiple source case.
Paper eliminates warm-up phase for PO in linear MDPs, achieving optimal regret.
problem Costly warm-up phase in PO algorithms for linear MDPs.
method Simple contraction mechanism replaces warm-up phase.
result Achieves rate-optimal regret with improved dependence on problem parameters.
We consider a market with fractional Brownian motion with stochastic integrals generated by the Riemann sums. We found that this market is arbitrage free if admissible strategies that are using observations with an arbitrarily small delay. Moreover, we found that this approach eliminates the discontinuity of the stocha…
Study robustness of polynomial neural networks using algebraic geometry.
problem Certify robustness radius of polynomial neural networks.
method Metric algebraic geometry, Euclidean distance degree, symbolic elimination, homotopy-continuation methods.
result Found decision boundaries with lower ED degree than generic cubic hypersurfaces.
Balances and eliminates base algorithms in bandits and RL to bound total regret.
problem Model selection in bandits and reinforcement learning with unknown optimal regret.
method Balances and eliminates base algorithms based on candidate regret bounds.
result Total regret bound is the best valid candidate regret bound times a small multiplicative factor.
We consider the related tasks of matrix completion and matrix approximation from missing data and propose adaptive sampling procedures for both problems. We show that adaptive sampling allows one to eliminate standard incoherence assumptions on the matrix row space that are necessary for passive sampling procedures. Fo…
Proposes a flexible tournament design combining knockout and round-robin.
problem Designing a tournament that eliminates participants linearly.
method Combines knockout and round-robin structures for flexible elimination.
result Flexible tournament design can eliminate participants linearly.
We generalise to the -graded set-up a practical method for inspecting the (non)removability of parameters in zero-curvature representations for partial differential equations (PDEs) under the action of smooth families of gauge transformations. We illustrate the generation and elimination of parameters in …
New method simplifies optimization landscapes by transforming saddle points.
problem Saddle points hinder non-convex optimization in machine learning.
method Variable elimination algorithms, like VarPro, are compared to reveal geometric insights.
result Variable elimination reshapes critical point structure, creating local maxima from saddle points.
The standard LSTM recurrent neural networks while very powerful in long-range dependency sequence applications have highly complex structure and relatively large (adaptive) parameters. In this work, we present empirical comparison between the standard LSTM recurrent neural network architecture and three new parameter-r…
Improved elimination strategies for adaptive bandit identification reduce sample complexity and computational burden.
problem Inefficient elimination strategies in bandit identification.
method Adaptive elimination methods that update sampling rules frequently and reduce problem size.
result Adaptive elimination methods achieve better sample complexity and computational efficiency.
Type system captures CI relationships for probabilistic models.
problem Challenges in inference for models with mixed discrete and continuous parameters.
method Information flow type system for probabilistic programming.
result Well-typed programs guarantee certain CI relationships.
This paper studies a class of exponential family models whose canonical parameters are specified as linear functionals of an unknown infinite-dimensional slope function. The optimal minimax rates of convergence for slope function estimation are established. The estimators that achieve the optimal rates are constructed …
Classification may not be reliable for several reasons: noise in the data, insufficient input information, overlapping distributions and sharp definition of classes. Faced with several possibilities neural network may in such cases still be useful if instead of a classification elimination of improbable classes is done…
A new policy for contextual bandits adapts to reward vector shifts.
problem Learning under reward vector shifts with ordered rewards.
method Adaptive-discretization and optimistic elimination policy.
result Established upper bounds on preference-based regret.
New algorithms eliminate stepsize tuning for bilevel optimization problems.
problem Bilevel optimization problems with unknown parameters and stepsizes.
method D-TFBO and S-TFBO algorithms with adaptive stepsizes.
result Achieve performance comparable to well-tuned approaches with theoretical guarantees.
New algorithm eliminates arms to minimize regret in complex bandit problems.
problem Minimizing regret in combinatorial bandit problems with explicit exploration.
method Introduces a novel arm elimination scheme that partitions arms into three categories and incorporates explicit exploration.
result Achieves near-optimal regret in combinatorial multi-armed and linear contextual bandit problems.
The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations. Ternary Connect (TC) \cite{lin2015neural} addresses this issue by restricting the parameters to three levels , and , thus eliminating multiplications in the forward pass of the net…
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination…
Paper compresses deep neural networks by eliminating redundant neurons.
problem Challenges in deploying deep learning models due to high parameter count.
method Exploits non-linear redundancy to compress neural networks without loss.
result Reduces network size by up to 99% with minimal performance loss.
We consider a multi-armed bandit problem in a setting where each arm produces a noisy reward realization which depends on an observable random covariate. As opposed to the traditional static multi-armed bandit problem, this setting allows for dynamically changing rewards that better describe applications where side inf…
Paper identifies resting positions using EGG, ECG, respiration rate, and SpO2.
problem Identifying the resting position for health monitoring.
method Hybrid stacked ensemble machine learning model combining Decision tree, Random Forest, and Xgboost.
result 100% accurate prediction of resting positions.
We introduce Neural Choice by Elimination, a new framework that integrates deep neural networks into probabilistic sequential choice models for learning to rank. Given a set of items to chose from, the elimination strategy starts with the whole item set and iteratively eliminates the least worthy item in the remaining …
We present an accelerated algorithm for hierarchical density based clustering. Our new algorithm improves upon HDBSCAN*, which itself provided a significant qualitative improvement over the popular DBSCAN algorithm. The accelerated HDBSCAN* algorithm provides comparable performance to DBSCAN, while supporting variable …
Aims to eliminate domain bias in authentication without domain labels.
problem Authentication models are biased due to domain differences.
method Discover latent domains and eliminate domain difference alternately, using a meta-learning framework.
result Eliminates domain difference in authentication without domain labels.
A new method uses physics-informed neural networks to solve reliability analysis problems without simulations.
problem Solving reliability analysis problems without the need for expensive simulations.
method Physics-informed neural networks to learn directly from problem physics.
result Eliminates the need for expensive simulations and achieves highly accurate results.
New algorithm identifies best arm in rested bandit setting.
problem Best arm identification in rested bandit with decreasing losses.
method Introduced a novel best arm identification problem and analyzed an arm elimination algorithm.
result Regret vanishes as time horizon increases, with convergence rate depending on expected loss function.
Transformers reduce redundancy by focusing on invariant relational quantities.
problem Substantial internal redundancy in Transformer models due to coordinate-dependent representations and continuous symmetries.
method Reformulate representations, attention mechanisms, and optimization dynamics in terms of invariant relational quantities, eliminating redundant degrees of freedom by construction.
result Architectures that operate directly on relational structures, providing a principled geometric framework for reducing parameter redundancy and analyzing optimization.
We simplify Khovanov homology for torus braids using Gaussian elimination.
problem Computing Khovanov homology for torus braids is complex and computationally intensive.
method Applying Gaussian elimination to reduce the number of generators in the Khovanov chain complex.
result We provide a bound on the number of generators in the whittled complex at fixed homological degree.
A wide class of machine learning algorithms can be reduced to variable elimination on factor graphs. While factor graphs provide a unifying notation for these algorithms, they do not provide a compact way to express repeated structure when compared to plate diagrams for directed graphical models. To exploit efficient t…
A Logic Based Approach to Finding Real Singularities of Implicit Ordinary Differential Equationsmath.LO
Logic approach finds real singularities in differential equations.
problem Finding geometric singularities of implicit ODEs over the reals.
method Vessiot theory, parametric Gaussian elimination, heuristic simplification, real quantifier elimination.
result Effective computation of geometric singularities using logic methods.
We develop an approach for feature elimination in statistical learning with kernel machines, based on recursive elimination of features.We present theoretical properties of this method and show that it is uniformly consistent in finding the correct feature space under certain generalized assumptions.We present four cas…
Efficient method defends privacy in federated learning without accuracy loss.
problem Privacy attacks on federated learning by reconstructing and identifying local data.
method Random noise perturbation method that allows recovery of true gradients.
result Strong privacy protection without sacrificing learning accuracy.
Proposes a new semi-parametric framework for batched bandits with covariates.
problem Sequential decision-making with batched feedback and contextual information.
method Batched single-Index Dynamic binning and Successive arm elimination (BIDS) using single-index regression.
result Achieves minimax-optimal rates for nonparametric batched bandits.
As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define individuals, but lack a discussion of certain features not being observed at test ti…
Two new feature selection algorithms improve on RFE.
problem Optimal feature selection for faster and more accurate models.
method Fibonacci and k-Subsecting Recursive Feature Elimination.
result Faster feature selection with comparable predictive performance.
Proposes a new method for selecting regularization parameters in sparse precision matrix estimation.
problem Selecting an appropriate regularization parameter for sparse precision matrix estimation.
method Developed a closed-form matrix-valued regularization parameter based on the sampling distribution of optimality conditions.
result The proposed method achieves comparable estimation accuracy and superior support recovery to cross-validation, with significant runtime improvements.
PoWER-BERT speeds up BERT inference by eliminating redundant word-vectors.
problem Improving BERT inference speed without sacrificing accuracy.
method Eliminating redundant word-vectors using a self-attention-based significance measure and learning the number of vectors to eliminate.
result Up to 4.5x reduction in inference time with <1% loss in accuracy on GLUE benchmark.
We propose a Conditional Density Filtering (C-DF) algorithm for efficient online Bayesian inference. C-DF adapts MCMC sampling to the online setting, sampling from approximations to conditional posterior distributions obtained by propagating surrogate conditional sufficient statistics (a function of data and parameter …
With the increasing size of today's data sets, finding the right parameter configuration in model selection via cross-validation can be an extremely time-consuming task. In this paper we propose an improved cross-validation procedure which uses nonparametric testing coupled with sequential analysis to determine the bes…
A new Bayesian framework simplifies stochastic optimization by focusing on key parameters.
problem Bayesian methods struggle with complex structural constraints.
method Minimalist Bayesian framework that eliminates nuisance parameters via profile likelihood.
result Near-optimal regret guarantees for multi-armed bandits and convex optimization.
Enhances quantum sensing by eliminating multiple oscillations in field amplitude estimation.
problem Multiple oscillations in field amplitude estimation due to inter-qubit interactions at high qubit densities.
method Adopting a quantum circuit learning framework to approximate a target function by optimizing gate parameters.
result Elimination of multiple oscillations, leading to enhanced dynamic range of quantum sensing.
Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parameter pruning methods usually drive weights towards zero with large and constant regularization factor…
GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.
problem Optimizing nonparametric contextual bandits with efficient regret bounds.
method Inspired by Policy Elimination, GPE uses oracle-efficient techniques for nonparametric classes with infinite VC-dimension.
result GPE is regret-optimal for policy classes with integrable entropy, and for larger entropy, it provides an -greedy algorithm with matching regret bounds.
New policy optimizes product assortment in the presence of unpredictable customers.
problem Optimizing product assortment in the presence of outlier customers.
method Developed a robust online assortment optimization policy using an active elimination strategy.
result Established upper and lower bounds on regret, showing optimality up to logarithmic factor in .
-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rankcs.LG
Paper tackles online learning in large MDPs with low Bellman rank using AVE algorithm.
problem Online learning of MDPs with large state spaces.
method Develops AVE algorithm inspired by OLIVE, using contextual bandit problems and elimination steps.
result Achieves -regret for learning optimal value function in MDPs with function approximation and low Bellman rank.