We present any-precision deep neural networks (DNNs), which are trained with a new method that allows the learned DNNs to be flexible in numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-widths, by truncating the least significant bits, to support dynamic …
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 “flexible trade-off”
Learning algorithms need bias to generalize and perform better than random guessing. We examine the flexibility (expressivity) of biased algorithms. An expressive algorithm can adapt to changing training data, altering its outcome based on changes in its input. We measure expressivity by using an information-theoretic …
Vecchia approximations provide the best accuracy-runtime trade-off for Gaussian process approximations.
problem High computational cost of Gaussian processes for large data sets.
method Systematic comparison of different Gaussian process approximations.
result Vecchia approximations consistently provide the best accuracy-runtime trade-off.
Enhances deep kernel learning with stochastic latent variables for better model regularization.
problem Weak model regularization in deep kernel learning, especially on small datasets.
method Introduces DLVKL model with stochastic latent variables, NSDE for expressive posterior, and hybrid prior.
result DLVKL-NSDE outperforms existing deep GPs on large datasets.
Adaptive batch sizes improve active learning efficiency and flexibility.
problem Fixed batch sizes in active learning are inefficient due to dynamic cost-speed trade-offs.
method Probabilistic Numerics framework that adaptively changes batch sizes based on integration error and precision objectives.
result Significant enhancement in learning efficiency and flexibility across various applications.
New framework for DP-SMO with near-optimal privacy-loss trade-off.
problem Optimal trade-off between privacy and population loss in DP-SMO.
method General framework using Phased-ERM method and black-box optimization.
result Near-linear time algorithms with near-optimal guarantees.
Proposes TCWAE to learn disentangled representations using the Wasserstein Autoencoder.
problem Balancing reconstruction fidelity and disentanglement in learning representations.
method TCWAE (Total Correlation Wasserstein Autoencoder) using different KL estimators.
result Competitive results on data sets with known generative factors, and improved reconstructions on unknown factors.
This paper analyzes the trade-off between accuracy and communication in personalized federated learning.
problem The accuracy-communication trade-off in personalized federated learning.
method The paper provides a quantitative characterization of the personalization degree on the trade-off, establishing minimax optimality.
result The paper offers theoretical insights for choosing the personalization degree and validates the results on synthetic and real-world datasets.
We introduce a flexible family of fairness regularizers for (linear and logistic) regression problems. These regularizers all enjoy convexity, permitting fast optimization, and they span the rang from notions of group fairness to strong individual fairness. By varying the weight on the fairness regularizer, we can comp…
A new model for point processes without intensity function trade-offs.
problem Inefficiency and trade-offs in existing point process models.
method Point Set Diffusion, a diffusion-based latent variable model.
result Achieves state-of-the-art performance in point process generation.
MGLM models all possible language channel factorizations for improved multilingual generation.
problem Generating multilingual text with flexibility and quality.
method Generative joint distribution model over language channels, marginalizing all possible factorizations.
result MGLM outperforms traditional models in multilingual generation tasks.
EHVI outperforms scalarized EI in MOBO for molecule design.
problem Benchmarking MOBO strategies for molecule design.
method Compared EHVI against fixed-weight scalarized EI in MOBO.
result EHVI consistently outperforms scalarized EI in molecular optimization tasks.
Improved neural image compression with refined latent representations.
problem Sub-optimal results from variational autoencoders due to imperfect optimization and capacity limitations.
method Stochastic Gumbel Annealing (SGA) and its extensions (SGA+), including three different methods.
result Significant improvement in compression performance, especially on the R-D trade-off.
This work introduces uncertainty principles to mitigate Maximal Extractable Value in blockchain systems.
problem Maximal Extractable Value (MEV) in decentralized systems due to transaction submission privacy and monopolist power.
method Unified approaches via uncertainty principles, akin to harmonic analysis and physics, to quantify trade-offs between transaction flexibility and user economic payoff.
result Demonstrates a quantitative trade-off between transaction flexibility and user economic payoff, analogous to the Nyquist-Shannon sampling theorem.
Joslim optimizes both width and weight configurations for slimmable neural networks, improving model efficiency.
problem Optimizing both width and weight configurations for slimmable neural networks to improve efficiency.
method Proposes a general framework for joint optimization of width configurations and weights, and introduces Joslim algorithm.
result Improves model efficiency by up to 1.7% in top-1 accuracy on the ImageNet dataset.
Proposes a variational autoencoder for long-term customer revenue forecasting.
problem Predicting long-term customer revenue from sparse and irregular transaction data.
method Variational Autoencoder (VAE) with flexible latent representation.
result Improves upon latest benchmarks in multiple real-world datasets.
Temporal point processes are the dominant paradigm for modeling sequences of events happening at irregular intervals. The standard way of learning in such models is by estimating the conditional intensity function. However, parameterizing the intensity function usually incurs several trade-offs. We show how to overcome…
GOAT improves attention mechanisms by learning better priors.
problem Standard attention mechanisms use a naive uniform prior, limiting flexibility and generalization.
method GOAT introduces a trainable, continuous prior that replaces the uniform assumption, maintaining compatibility with optimized kernels.
result GOAT avoids representational trade-offs and learns an extrapolatable prior that combines positional flexibility with length generalization.
New methods accelerate NCGP inference by trading computation for uncertainty.
problem Prohibitively expensive exact inference in NCGPs for large datasets.
method Iterative methods explicitly modeling approximation error, leveraging parallel computing.
result Significant acceleration of posterior inference compared to baselines.
SHAKE-GNN scales GNNs for large graphs with multi-scale representations.
problem Scaling Graph Neural Networks (GNNs) to large graphs.
method SHAKE-GNN uses a hierarchy of Kirchhoff Forests for stochastic multi-resolution graph decompositions.
result SHAKE-GNN achieves competitive performance on large-scale graph classification benchmarks.
Modeling complex conditional distributions is critical in a variety of settings. Despite a long tradition of research into conditional density estimation, current methods employ either simple parametric forms or are difficult to learn in practice. This paper employs normalising flows as a flexible likelihood model and …
FlexAE addresses bias-variance trade-off in RAEs by learning latent priors.
problem Improving generation quality of deterministic AE models.
method Introducing flexibly learnable latent priors in WAEs to optimize the latent distribution.
result FlexAE achieves state-of-the-art performance in AE-based generative models.
Paper tackles federated learning with personalised bandit algorithms.
problem Optimizing local and global objectives in a heterogeneous environment.
method Surrogate objective function combining client preferences and global knowledge; phase-based elimination algorithm.
result Achieves sublinear regret with logarithmic communication overhead.
Fast and Robust Likelihood-Guided Diffusion Posterior Sampling with Amortized Variational Inferencestat.ML
Improved diffusion sampling for inverse problems with faster and more robust inference.
problem High computational cost and lack of robustness in diffusion posterior sampling.
method Amortized variational inference with explicit likelihood guidance.
result Improved trade-off between inference speed and robustness to unseen degradations.
Principal component analysis balancing prediction and approximation accuracy for spatial datastat.ME
New algorithm balances spatial data approximation and prediction accuracy.
problem Lack of methods considering spatial correlation and downstream modeling in dimension reduction.
method Formalizes approximation and modeling utility as metrics, proposes a balanced algorithm.
result Optimal trade-off between approximation accuracy and downstream modeling utility.
Inference is an integral part of probabilistic topic models, but is often non-trivial to derive an efficient algorithm for a specific model. It is even much more challenging when we want to find a fast inference algorithm which always yields sparse latent representations of documents. In this article, we introduce a si…
Study optimizes fairness in predictive models by balancing utility and separation.
problem Balancing fairness and utility in predictive models.
method Information-theoretic approach using conditional mutual information (CMI).
result Reduces separation violations while maintaining or improving utility.
Proposes ELASTICBSP for faster, more flexible distributed deep learning training.
problem Inefficient synchronization in classic BSP for distributed deep learning.
method Introduces ELASTICBSP model with ZIPLINE method for more flexible training.
result ELASTICBSP converges faster and more accurately than classic BSP.
This work improves multi-modal generative models by using permutation-invariant neural networks.
problem Improving multi-modal generative models with tighter variational objectives.
method Developed more flexible aggregation schemes based on permutation-invariant neural networks.
result Our variational objective and flexible aggregation models can better approximate the true joint distribution.
Proposes a method to create fair ITRs that balance value and fairness.
problem Fairness issues in ITRs that can lead to unfair advantages or disadvantages.
method Optimal transport theory to transform optimal ITRs into fair ITRs.
result Established a theoretical upper bound on value loss for improved trade-off ITRs.
Flexible spatial models improve predictive performance over nonstationary alternatives.
problem Improving predictive performance in nonstationary spatial modeling.
method Introduces a modular parametric covariance function that extends nonstationary spatial models.
result The proposed covariance function outperforms nonparametric methods in predictive performance.
Determinantal point processes (DPPs) offer a powerful approach to modeling diversity in many applications where the goal is to select a diverse subset. We study the problem of learning the parameters (the kernel matrix) of a DPP from labeled training data. We make two contributions. First, we show how to reparameterize…
TensorOpt finds optimal parallelization strategies for DNN training.
problem Finding efficient parallelization strategies for DNN training.
method TensorOpt uses an algorithm (FT) to search for an optimal set of parallelization strategies considering multiple objectives.
result TensorOpt provides accurate runtime cost estimation and adapts to resource availability.
This work improves federated learning privacy and accuracy with non-private data sharing and approximate gradient coding.
problem Challenges of non-IID data and stragglers in federated learning.
method Data-driven strategy combining offline data sharing and approximate gradient coding.
result Achieves a trade-off between privacy and utility, leading to improved model convergence and accuracy.
Three approaches learn personalized treatment policies for UTI patients.
problem Learning optimal treatment policies in multiobjective settings with fully observed outcomes.
method Indirect and direct approaches using predictive models and without intermediate models.
result All approaches outperform clinicians in achieving better performance on all outcomes and trade-offs.
A new method for selective classification trades off accuracy for coverage.
problem Selective classification allows a classifier to abstain from predicting some instances.
method Optimizes a collection of class-wise decoupled one-sided empirical risks.
result The method achieves near-optimal coverage in high target accuracy regimes.
We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward deep neural network that allows selective execution. Given an input, only a subset of D2NN neurons are executed, and the particular subset is determined by the D2NN itself. By pruning unnecessary computation depending on input, D2NNs provide a…
DeepRV accelerates spatiotemporal inference using neural priors.
problem Intractable scaling of Gaussian Processes for large datasets.
method Neural-network surrogate replacing GP prior sampling with complexity.
result DeepRV achieves highest fidelity to exact GPs while significantly speeding up inference.
This paper identifies drift Lipschitz budget K as key to diffusion policy expressivity and statistical trade-offs.
problem Understanding and maximizing the expressivity of diffusion policies while managing statistical limitations.
method Identifying drift Lipschitz budget K as central, quantifying expressivity and statistical behavior, proving lower bounds, and providing practical implementation guidelines.
result Balancing expressivity and statistical complexity yields a finite-sample performance gap, with rates depending on sample size and drift type.
Grad-TTS models speech from text using diffusion probabilistic techniques.
problem Creating high-quality speech from text input.
method Score-based decoder with stochastic differential equations for noise-to-speech transformation.
result Grad-TTS produces mel-spectrograms from text input with competitive quality.
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
problem Limitation of existing L2D frameworks to single-expert deferral.
method Top- Learning-to-Defer framework, including adaptive Top- variant.
result Superior accuracy-cost trade-offs with multi-expert deferral.
This paper describes a recursive estimation procedure for multivariate binary densities (probability distributions of vectors of Bernoulli random variables) using orthogonal expansions. For covariates, there are basis coefficients to estimate, which renders conventional approaches computationally prohibitive …
In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlar…
Matrix factorization methods are extensively employed to understand complex data. In this paper, we introduce the cross-product penalized component analysis (XCAN), a sparse matrix factorization based on the optimization of a loss function that allows a trade-off between variance maximization and structural preservatio…
Deep neural networks for ordinal outcomes combining image and tabular data.
problem Lack of interpretable models for ordinal outcomes in mixed data types.
method Ordinal Neural Network Transformation Models (ONTRAMs) integrating DL and classical ordinal regression.
result ONTRAMs achieve performance equivalent to standard multi-class DL models but are faster and more interpretable.
Environmental acoustic sensing involves the retrieval and processing of audio signals to better understand our surroundings. While large-scale acoustic data make manual analysis infeasible, they provide a suitable playground for machine learning approaches. Most existing machine learning techniques developed for enviro…
FNNs can be made more interpretable with statistical methods.
problem FNNs lack interpretability and are often used as black-box models.
method Supplement FNNs with statistical inference and covariate-effect visualizations.
result FNNs can be made more like traditional statistical models.
Gaussian processes (GPs) are flexible models that can capture complex structure in large-scale dataset due to their non-parametric nature. However, the usage of GPs in real-world application is limited due to their high computational cost at inference time. In this paper, we introduce a new framework, \textit{kernel di…