Estimates MLP expected output without sampling, using fewer FLOPs.
problem Estimating expected loss in machine learning efficiently.
method Approximate representations of activations using cumulants and Hermite expansions.
result Estimates expected output with fewer FLOPs than Monte Carlo sampling.
Reverse sensitivity analysis for risk models under various stresses.
problem Understanding model changes under output stress.
method Deriving the closest stressed distribution and model parameters.
result Numerically efficient method for calculating stressed model.
We consider the problem of joint modelling of metabolic signals and gene expression in systems biology applications. We propose an approach based on input-output factorial hidden Markov models and propose a structured variational inference approach to infer the structure and states of the model. We start from the class…
Bayesian optimization of function networks using intermediate outputs.
problem Efficiently optimizing networks of functions with significant evaluation time.
method Modeling nodes as Gaussian processes and using expected improvement acquisition function.
result Demonstrates superior performance compared to standard Bayesian optimization methods.
Optimizes target value in stochastic black box functions.
problem Finding input to minimize expected squared error to target value.
method Derives acquisition functions for expected improvement, probability of improvement, and lower confidence bound, assuming Gaussian aleatoric effects.
result Acquisition functions can outperform classical Bayesian optimization under certain conditions.
A new neural network model predicts inflation and output gap more accurately.
problem Traditional Phillips curves struggle with unobserved inflation expectations and output gaps.
method Hemisphere Neural Network (HNN) that estimates latent states for inflation and output gap.
result HNN accurately forecasts inflation and identifies a large positive output gap starting from late 2020.
Maxout networks study gradients and propose initialization strategies.
problem Complexity in input-output Jacobian distribution complicates stable parameter initialization.
method Obtained bounds on moments of gradients and formulated initialization strategies.
result Parameter initialization strategies improve training of deep maxout networks.
RePULSe improves language model alignment by reducing undesired outputs without sacrificing overall performance.
problem Aligning language models with human preferences while minimizing undesired outputs.
method Integrates probabilistic inference into RL training to reduce undesired outputs.
result RePULSe achieves a better balance between expected reward and undesired output probability.
Spatio-temporal problems are ubiquitous and of vital importance in many research fields. Despite the potential already demonstrated by deep learning methods in modeling spatio-temporal data, typical approaches tend to focus solely on conditional expectations of the output variables being modeled. In this paper, we prop…
We study algebraic varieties of ReLU networks to understand their representable functions.
problem Understanding the functions that ReLU neural networks can represent.
method We introduce algebraic varieties associated with ReLU networks and derive polynomial equations to characterize representable functions.
result Conditions under which ReLU networks attain their expected dimension, providing insight into their structural properties.
We consider optimization of composite objective functions, i.e., of the form f(x)=g(h(x)), where h is a black-box derivative-free expensive-to-evaluate function with vector-valued outputs, and g is a cheap-to-evaluate real-valued function. While these problems can be solved with standard Bayesian optimization, we…
A new method calculates optimal decisions from classifier outputs, improving predictions in drug discovery.
problem Finding optimal decisions from classifier outputs in fields like medicine.
method Develops a transducer that calculates probabilities from classifier outputs, enabling expected-utility maximization.
result Improves prediction accuracy in drug discovery problems, sometimes close to theoretical maximum.
New algorithm identifies good arms with fewer samples when thresholds are close.
problem Good arm identification in bandit problems with small threshold gaps.
method Proposes lil'HDoC algorithm to improve GAI under small threshold gaps.
result Sample complexity of first λ output arm is nearly identical to HDoC algorithm when thresholds are close.
Models such as Sequence-to-Sequence and Image-to-Sequence are widely used in real world applications. While the ability of these neural architectures to produce variable-length outputs makes them extremely effective for problems like Machine Translation and Image Captioning, it also leaves them vulnerable to failures o…
We present a novel methodology based on a Taylor expansion of the network output for obtaining analytical expressions for the expected value of the network weights and output under stochastic training. Using these analytical expressions the effects of the hyperparameters and the noise variance of the optimization algor…
Paper improves generalization bounds for structured output prediction problems.
problem Large label sets in structured output prediction problems.
method Developed novel high-probability bounds and generalization bounds in expectation.
result Significantly improved generalization bounds with logarithmic dependency on label set size.
Multi-output is essential in machine learning that it might suffer from nonconforming residual distributions, i.e., the multi-output residual distributions are not conforming to the expected distribution. In this paper, we propose "Wrapped Loss Function" to wrap the original loss function to alleviate the problem. This…
In many applications of supervised learning, multiple classification or regression outputs have to be predicted jointly. We consider several extensions of gradient boosting to address such problems. We first propose a straightforward adaptation of gradient boosting exploiting multiple output regression trees as base le…
A new method reduces both input and output dimensions for better goal-oriented analysis.
problem Simultaneous reduction of input and output dimensions for more accurate analysis.
method Coupled input-output dimension reduction, optimizing gradient-based bounds.
result Determine most informative sensors and influential parameters efficiently.
Sampling is a fundamental technique, and sampling without replacement is often desirable when duplicate samples are not beneficial. Within machine learning, sampling is useful for generating diverse outputs from a trained model. We present an elegant procedure for sampling without replacement from a broad class of rand…
GBC methods compute expected utility without needing the model's density.
problem Computing expected utility in complex models.
method Density-free generative method using quantile neural estimator.
result Efficient estimation of expected utility from simulated data.
Investment strategy for DC pension plan with inflation risk and tail VaR constraint.
problem Maximizing terminal wealth for pension member with tail VaR constraint.
method Lagrange method and quantile optimization techniques.
result Optimal investment strategy and output in closed-form derived.
Proposes a flexible MGP model for dynamic, sparse correlations.
problem Handling dynamic and sparse correlations in multivariate data.
method Non-stationary MGP with dynamic spike-and-slab prior and EM algorithm.
result Captures dynamic and sparse correlations effectively.
Bayesian optimization has demonstrated impressive success in finding the optimum input x* and output f* = f(x*) = max f(x) of a black-box function f. In some applications, however, the optimum output f* is known in advance and the goal is to find the corresponding optimum input x*. In this paper, we consider a new sett…
We propose to learn a kernel-based message operator which takes as input all expectation propagation (EP) incoming messages to a factor node and produces an outgoing message. In ordinary EP, computing an outgoing message involves estimating a multivariate integral which may not have an analytic expression. Learning suc…
Proposes FOAGP for efficient orthogonal effect decomposition of black-box computer experiments.
problem Challenges in sensitivity analysis of black-box computer experiments with complex, nonlinear functional outputs.
method Functional-output orthogonal additive Gaussian process (FOAGP) with conditional orthogonality constraint.
result Demonstrates effectiveness in orthogonal effect decomposition and variance decomposition through simulations and real-world application.
Unified framework for training SNNs using EP, faster convergence.
problem Training spiking neural networks with Expectation-Propagation.
method Message-passing framework for learning marginal distributions of SNN parameters.
result Faster convergence compared to gradient-based methods.
Study on deep neural networks using concentration inequalities and optimal stopping.
problem Understanding the performance and structure of stochastic deep neural networks.
method Introduced concentration inequalities for SDNN outputs and an EC classifier. Determined the optimal number of layers via an optimal stopping procedure.
result Optimal number of layers for SDNNs determined via an optimal stopping procedure.
We proposed the expected energy-based restricted Boltzmann machine (EE-RBM) as a discriminative RBM method for classification. Two characteristics of the EE-RBM are that the output is unbounded and that the target value of correct classification is set to a value much greater than one. In this study, by adopting featur…
We collect and analyze the data for working time, life expectancy, and the pair output and infrastructure of industrializing nations. During S-functional recovery from disaster the pair's time shifts yield 25 years for the infrastructure's physical lifetime. At G7 level the per capita outputs converge and the time shif…
Controller seeks informative system observations to predict nonlinear dynamics.
problem Predicting nonlinear dynamics with uncertain parameters.
method Expected free energy minimization for balancing goal state and informative observations.
result Controller improves performance in uncertain parameter scenarios.
We introduce a new sampling method for large language models that balances diversity and parallelism.
problem Balancing diversity and parallelism in decoding for large language models.
method Arithmetic sampling framework compatible with various sampling variations.
result Improves estimation of expected BLEU score reward and reduces the gap with beam search.
Adapts EGOP to multi-class setting and proposes a simple rough estimator.
problem Recovering relevant directions for multi-class regression.
method Adapt EGOP to multi-class setting, propose a simple rough estimator.
result Simple rough estimator of EJOP remains statistically consistent.
Study shows limitations and possibilities of learning quantum circuit output distributions.
problem Learnability of output distributions of local quantum circuits.
method Investigated within two oracle models: statistical query model and direct sample access model.
result Output distributions of super-logarithmic depth Clifford circuits are not efficiently learnable in the statistical query model.
ReLU networks don't exponentially distort curve lengths as previously thought.
problem Understanding how neural networks distort curve lengths with depth.
method Analyzing expected length distortion of ReLU networks with random initialization.
result Expected length distortion does not grow with depth, and shrinks slightly.
We study distributed learning with the least squares regularization scheme in a reproducing kernel Hilbert space (RKHS). By a divide-and-conquer approach, the algorithm partitions a data set into disjoint data subsets, applies the least squares regularization scheme to each data subset to produce an output function, an…
The key idea of Bayesian optimization is replacing an expensive target function with a cheap surrogate model. By selection of an acquisition function for Bayesian optimization, we trade off between exploration and exploitation. The acquisition function typically depends on the mean and the variance of the surrogate mod…
In most classification tasks there are observations that are ambiguous and therefore difficult to correctly label. Set-valued classifiers output sets of plausible labels rather than a single label, thereby giving a more appropriate and informative treatment to the labeling of ambiguous instances. We introduce a framewo…
Dropout neural networks can approximate any function with high probability.
problem Approximating functions with dropout neural networks.
method Two universal approximation theorems for dropout neural networks in random and deterministic modes.
result Dropout neural networks can approximate any function in probability and in Lq. This paper recovers input data from transformer models using attention weights.
problem Recovering input data from transformer models for security and privacy concerns.
method Introducing an algorithm to minimize the loss function between expected and actual outputs of transformers.
result The algorithm successfully recovers input data from attention weights and outputs of transformers.
This paper enhances privacy in statistical model checking of cyber-physical systems.
problem Privacy concerns in consumer-level applications due to statistical model checking.
method Proposes expected differential privacy and a new exponential mechanism for sequential algorithms.
result Demonstrates a novel mechanism to preserve privacy in statistical model checking.
Distillation speeds up classifier training and provides insights into its success.
problem Empirical success of knowledge distillation without theoretical explanation.
method Study of linear and deep linear classifiers, proving a generalization bound.
result Three key factors for distillation success: data geometry, optimization bias, strong monotonicity.
We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. When the input distribution is known, there already exists an algorithm having an expected excess…
This paper improves deep learning model consistency through ensemble methods.
problem Consistency and correct-consistency issues in deep learning models.
method Formal definition of consistency and correct-consistency, proving ensemble improvement, proposing dynamic snapshot ensemble method.
result Ensemble methods can improve correct-consistency of deep learning models.
New EM algorithm improves deep generative network training.
problem Training deep generative networks with complex posterior and likelihood distributions.
method Derive analytical posterior and marginal distributions using CPA property, derive analytical EM algorithm.
result EM training yields higher likelihood than Variational Autoencoders (VAEs).
Paper proposes efficient communication scheme for statistical learning.
problem Efficiently conveying a statistical hypothesis from a client to a server.
method Joint training and source coding scheme with KL divergence constraints.
result Guarantees small average empirical risk, generalization error, and communication cost.
Introduces foundation priors for using model-generated data in empirical research.
problem Using model-generated data as real observations in empirical research.
method Introduces foundation priors as an exponential-tilted, generalized Bayesian update of the user's primitive prior.
result Synthetic data reflects both model patterns and user's priors, enabling principled use in empirical work.
Bayesian method for estimating quantile sets efficiently.
problem Estimating quantile sets of expensive-to-evaluate functions.
method Bayesian active learning with Gaussian process modeling and Expected Estimator Modification (EEM).
result Efficient estimation of small quantile sets.