We extend neural networks with fractional and mixed activation functions for better function approximation.
problem Limitations in approximating higher-order smooth functions in complex spaces.
method Incorporating fractional exponents in activation functions and defining new density functions.
result Improved accuracy and broader applicability of neural network approximation theory.
Token-adaptive FFN design improves LLM expressivity.
problem Fixed activation functions limit FFN expressivity in LLMs.
method Mixture of Activations (MoA) and learnable activations (LA).
result MoA achieves lower terminal loss and better scaling than baselines.
Optimizes routing in decentralized exchanges with gas fees.
problem Routing in decentralized exchanges with fixed gas fees.
method General optimization framework with mixed-integer model, incorporating gas fees.
result Explicit Karush-Kuhn-Tucker system linking prices, fees, and activation.
New proof shows neural networks can memorize training data with high accuracy.
problem Proving neural networks can memorize training data with high accuracy.
method Probabilistic construction exploiting sparsity.
result Proves neural networks with threshold or mixed threshold-ReLU activations can memorize training data.
Develops a functional mix-of-experts model for multiclass classification.
problem Multiclass classification with univariate functional predictors.
method Functional mix-of-experts model with regularization and sparsity constraints.
result Regularized maximum likelihood estimation yields interpretable coefficient functions.
Unified formula for training dynamics of linear networks combining lazy and balanced regimes.
problem Training dynamics of linear networks in two distinct setups: lazy and balanced/active.
method Unified formula for the evolution of the learned matrix, combining lazy and balanced regimes.
result Unified formula allows for rapid convergence and low rank bias, proving a complete phase diagram.
Mixed likelihood GPs improve model performance in human-in-the-loop experiments.
problem Lack of auxiliary information in traditional GPs for human responses.
method Propose mixed likelihood variational GPs to leverage auxiliary information.
result Modeling performance improvements across diverse applications.
Efficient Bitwidth Search optimizes neural network quantization for better performance.
problem Finding optimal bitwidth for weights and activations of each layer efficiently.
method EBS algorithm reusing meta weights and binary decomposition for efficient mixed precision convolution.
result Mixed precision QNN outperforms uniform bitwidth and other techniques on CIFAR10 and ImageNet.
New algorithms optimize neural networks with ReLU activations using sampling.
problem Optimizing trained neural networks with ReLU activations.
method Iterative algorithm and enhanced algorithm using sampling and neighborhood search.
result The methods reduce the initial MIP problem into smaller LP or MIP problems.
New MMM captures hierarchical marketing effects and sign restrictions.
problem Measuring effectiveness of marketing activities with hierarchical structure and sign constraints.
method Proposes a constrained maximum likelihood approach using Hamiltonian Monte Carlo algorithm.
result Demonstrates superior performance on real datasets compared to multi-stage methods.
New neural network with RePU activation approximates smooth functions and their derivatives.
problem Approximating smooth functions and their derivatives with neural networks.
method Differentiable neural networks with RePU activation functions.
result Improved approximation error bounds for RePU-activated neural networks.
New research limits how deep neural networks can be for certain functions.
problem Understanding the depth required for neural networks to represent specific functions.
method Mixed-integer optimization, polyhedral theory, tropical geometry.
result Neural networks with more than one layer are necessary to represent certain functions.
Optimizes marketing strategies with practical constraints.
problem Adjusting marketing activities with minimum and maximum changes.
method Formulated as a mixed integer nonlinear program (MINLP), reformulated for computational efficiency.
result Significant improvements in solution process for realistic problems.
A new MARL framework for community-based cooperation with transfer and active exploration.
problem Flexible coordination patterns in multi-agent systems with community structures.
method Community-based multi-agent reinforcement learning with transfer and active exploration.
result Provably convergent actor-critic algorithms for structured information sharing and transfer learning.
Proposes an efficient algorithm for mHealth that makes real-time physical activity suggestions.
problem Training complex models efficiently in real-time mHealth applications.
method Streamlined empirical Bayes procedure for fitting linear mixed effects models.
result Improves accuracy and speed over state-of-the-art approaches in mHealth applications.
Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.
problem Memory limitations prevent accurate deployment of DNN models on tiny MCUs.
method Automated mixed-precision quantization using Reinforcement Learning for MCU constraints.
result Mixed-precision models achieve high accuracy with uniform quantization policies.
ReLU networks trained with MILPs match deep learning accuracy.
problem Training deep neural networks efficiently.
method Iterative training with Mixed Integer Linear Programs (MILPs).
result ReLU networks can be trained with MILPs achieving similar accuracy to deep learning methods.
Theoretical analysis of deep neural networks for time series data.
problem Theoretical development for deep neural networks on temporally dependent observations is lacking.
method Established non-asymptotic bounds for prediction error of deep neural networks under mixing-type assumptions.
result Deep neural networks can model non-linear time series data with additional logarithmic factors due to dependence.
Source imaging based on magnetoencephalography (MEG) and electroencephalography (EEG) allows for the non-invasive analysis of brain activity with high temporal and good spatial resolution. As the bioelectromagnetic inverse problem is ill-posed, constraints are required. For the analysis of evoked brain activity, spatia…
Deep learning has shown high performances in various types of tasks from visual recognition to natural language processing, which indicates superior flexibility and adaptivity of deep learning. To understand this phenomenon theoretically, we develop a new approximation and estimation error analysis of deep learning wit…
Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning systems in the wild. To guard against adversarial examples, we take inspiration from game theory and ca…
New MIP approach for efficient change-point detection.
problem Offline multiple change-point detection in data streams.
method Mixed-integer programming (MIP) for globally optimal PWL fitting.
result Provable tighter relaxations for segment assignment variables.
Unified Skew-Gaussian process framework for various regression and classification tasks.
problem Handling multiple types of regression and classification problems.
method Generalization of Skew-Gaussian processes to handle various types of data and likelihoods.
result Closed-form posterior distributions for multiple tasks.
Study long-only minimum variance portfolio in one-factor market with arbitrary sign betas.
problem Characterize the long-only minimum variance portfolio in a one-factor market with mixed-sign betas.
method Explicit solution for long-only minimum variance portfolio, explicit characterization of active set, asymptotic analysis in high-dimensional regime.
result Proportion of active assets in LOMV portfolio converges to F(β∗) in high-dimensional regime, with rate O(F(0)1/3) when F(0)>0. DANTE trains neural networks using an alternating minimization approach.
problem Training neural networks with mixed activation functions efficiently.
method DANTE uses alternating minimization and quasi-convexity to handle neural networks with both differentiable and non-differentiable activation functions.
result DANTE-trained neural networks are promising and competitive in terms of quality and training speed.
Meta-active learning optimizes control of safety-critical systems by efficiently learning dynamics and configurations.
problem Efficiently learning system dynamics and optimal configurations for safety-critical systems like deep brain stimulation.
method Meta-learning an acquisition function using LSTM, cast as meta-learning, with a mixed-integer linear program policy.
result Achieved a 46% increase in information gain and a 20% speedup in computation time over baselines.
Deep learning classifies autism vs controls with high accuracy using large fMRI dataset.
problem Classification difficulty of autism vs typically developing controls with fMRI data.
method Ensemble CNN model trained on 43,858 fMRI datapoints, employing class-balancing and visualization methods.
result Deep learning models achieve AUROCs of 0.6774, 0.7680, and 0.9222 for ASD vs TD, gender, and task vs rest classifications.
This paper studies four trading algorithms of a professional trader at a multilateral trading facility, observing a realistic two-sided limit order book whose dynamics are driven by the order book events. The identity of the trader can be either internalizing or regular, either a hedge fund or a brokery agency. The spe…
Bayesian model clusters brain activity time series.
problem Heterogeneous multivariate time series in brain imaging.
method Group-based Bayesian mixture of smoothing splines with covariate effects.
result Distinct brain activity patterns identified.
Study examines active travel in Chicago communities, revealing mixed perceptions.
problem Transport disadvantage and lack of active mobility in underserved communities.
method Focus groups, qualitative discourse analysis, quantitative text-mining (topic modeling, sentiment analysis).
result Residents view active travel as both necessity and symbol of privilege, influenced by local culture.
Mixed precision DNNs improve performance with learned parametrization of quantizers.
problem Achieving optimal bitwidths for efficient inference on mobile devices.
method Differentiable quantization with straight-through gradients to learn bitwidths from step size and dynamic range.
result A suited parametrization of the quantizer is key to stable training and good performance.
Bayesian method selects subsets for LMMs with structured dependence.
problem Subset selection challenge in LMMs with structured dependence.
method Bayesian decision analysis with Mahalanobis loss function.
result Optimal linear coefficients for subsets and cardinality constraints.
MPTE uses Transformer attention to estimate mixed-frequency factor models.
problem Estimating factor models in panel datasets with mixed frequencies and nonlinear signals.
method Mixed-Panels-Transformer Encoder (MPTE) with attention mechanisms.
result MPTE achieves competitive performance in nonlinear forecasting environments.
While active learning offers potential cost savings, the actual data efficiency---the reduction in amount of labeled data needed to obtain the same error rate---observed in practice is mixed. This paper poses a basic question: when is active learning actually helpful? We provide an answer for logistic regression with t…
Residual Flows improve flow-based models for density estimation.
problem Density estimation using flow-based models with biased log-density estimates.
method Proposed a Russian roulette estimator for unbiased log-density estimation and used an alternative infinite series for gradient calculation. Improved invertible residual blocks with activation functions avoiding derivative saturation and generalized Lipschitz condition to induced mixed norms.
result Residual Flows achieve state-of-the-art performance on density estimation and outperform coupling block networks in joint generative and discriminative modeling.
SMT-EX enhances SMT for explaining surrogate models of mixed-variable design problems.
problem Making decisions and understanding complex systems using surrogate models of mixed-variable design problems.
method Integrates explainability techniques into SMT, including Shapley Additive Explanations, Partial Dependence Plot, and Individual Conditional Expectations.
result Demonstrates versatility in addressing diverse problem characteristics.
New approach models computer network activity as mixtures of sources.
problem Malicious activity detection in computer networks using standard algorithms is ineffective.
method Source separation approach to model short-term dynamics of computer network activity.
result Qualitative and quantitative experiments validate the approach.
Graph Signal Processing (GSP) is a promising framework to analyze multi-dimensional neuroimaging datasets, while taking into account both the spatial and functional dependencies between brain signals. In the present work, we apply dimensionality reduction techniques based on graph representations of the brain to decode…
MiVaBo optimizes mixed-variable functions efficiently, handling constraints.
problem Optimizing expensive, mixed-variable functions with discrete constraints.
method Combines linear surrogate model and Thompson sampling, optimizing acquisition function.
result First BO method to handle complex constraints over discrete variables.
The seemingly stochastic transient dynamics of neocortical circuits observed in vivo have been hypothesized to represent a signature of ongoing stochastic inference. In vitro neurons, on the other hand, exhibit a highly deterministic response to various types of stimulation. We show that an ensemble of deterministic le…
We can compare the expressiveness of neural networks that use rectified linear units (ReLUs) by the number of linear regions, which reflect the number of pieces of the piecewise linear functions modeled by such networks. However, enumerating these regions is prohibitive and the known analytical bounds are identical for…
Maximizes mixing efficiency in surface braids.
problem Finding the maximum mixing efficiency in surface braids.
method Introduced an efficient algorithm to compute topological entropy and TEPO for surface braids.
result Conjectured a novel candidate braid to have maximal mixing efficiency.
A new algorithm tackles active exploration in noisy MDPs.
problem Accurately estimating state mean values in MDPs with varying noise levels.
method Introduces a novel learning algorithm to balance exploration and exploitation.
result Active exploration in MDPs can be more challenging than in MAB.
Study on singularities of specific polynomial functions.
problem Characterizing the topology of singularities of mixed functions.
method Introduced inner non-degenerate mixed functions and used Newton boundary to characterize links.
result Links of singularities can be completely characterized under certain conditions.
Optimizes pension mix of PAYGO, EET, and individual savings.
problem Balancing PAYGO, EET, and individual savings in funded pension schemes.
method Solves a Nash equilibrium between pension participants and government, considering age-dependent preferences and optimal asset allocation.
result Identifies critical ages and optimal contribution rates for maximizing overall utility.
The paper bounds the excess risk of deep neural networks for weakly dependent processes.
problem Learning with weakly dependent data using deep neural networks.
method Approximation of smooth functions by deep neural networks and a bound on excess risk.
result The excess risk bound for deep learning under weak dependence is close to O(n−1/2) for sufficiently smooth functions. Bayesian optimization with binary auxiliary info for faster target function optimization.
problem Optimizing target functions with expensive binary auxiliary information.
method Mixed-type Gaussian process (MOGP) and information-based acquisition functions (MT-ES, MT-PES).
result Efficient approximation of mixed-type predictive ES via random features.
Characterizes continuity of monotone functionals in mixed topology.
problem Continuity of monotone functionals in mixed topology.
method Characterization through lower semicontinuity and dual representations.
result Continuity in mixed topology is equivalent to dual representation in terms of countably additive measures.