LSQ+ improves quantization of neural nets with Swish activations, achieving state-of-the-art results.
problem Quantization of neural nets with Swish activations, especially negative activations, leads to significant performance loss.
method Introduces learnable scale and offset parameters for asymmetric quantization, and uses MSE-based initialization for quantization parameters.
result Significantly outperforms LSQ for low-bit quantization of neural nets with Swish activations, achieving up to 5.6% gain with W2A2 quantization of EfficientNet-B0.
This work shows MLPs can approximate monotonic functions without bounded activations.
problem Optimizing MLPs with monotonic constraints and bounded activations.
method Generalized theoretical results showing MLPs with non-negative weights and saturating activations are universal approximators.
result MLPs with non-negative weights and saturating activations are universal approximators for monotonic functions.
Bayesian active learning tackles nuisance parameters, leading to bias and dilemmas.
problem Bayesian active learning with nuisance parameters leads to bias and dilemmas.
method Characterizes and mitigates negative interference by accurately estimating nuisance parameters.
result The extent of negative interference can be extremely large, and accurate estimation of nuisance parameters is critical.
GOLS finds activation functions affect training robustness, especially ReLU.
problem Investigate how different activation functions impact GOLS in neural network training.
method Identify SNN-GPPs for GOLS, analyze activation function effects on gradient continuity.
result GOLS robust for most activation functions but sensitive to ReLU.
In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear unit (PReLU) and a new randomized leaky rectified linear units (RReLU). We evalu…
Activation functions are essential for deep learning methods to learn and perform complex tasks such as image classification. Rectified Linear Unit (ReLU) has been widely used and become the default activation function across the deep learning community since 2012. Although ReLU has been popular, however, the hard zero…
Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input data and act as a selection mechanism that ensures sparsity of the representati…
We prove a negative result for the approximation of functions defined on compact subsets of Rd (where d≥2) using feedforward neural networks with one hidden layer and arbitrary continuous activation function. In a nutshell, this result claims the existence of target functions that are as difficult to…
New model shows negative resilience can improve trading efficiency.
problem Optimal trade execution in limit order books with negative resilience.
method Stochastic order book model with negative resilience.
result Negative resilience can lead to more efficient trading.
Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels. The learning algorithm must thus select which unlabeled examples to use as negative training points, possibly ending up wit…
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research. In this work, we study the loss landscape of deep networks through the eigendecompositions of their Hessian matrix. In particular, we examine how important the negative eigenvalu…
We propose a new notion of `non-linearity' of a network layer with respect to an input batch that is based on its proximity to a linear system, which is reflected in the non-negative rank of the activation matrix. We measure this non-linearity by applying non-negative factorization to the activation matrix. Considering…
Recently, self-normalizing neural networks (SNNs) have been proposed with the intention to avoid batch or weight normalization. The key step in SNNs is to properly scale the exponential linear unit (referred to as SELU) to inherently incorporate normalization based on central limit theory. SELU is a monotonically incre…
ICAL improves deep learning model accuracy and NLL with optimized batch labeling.
problem Deep Bayesian Active Learning for efficient model training.
method ICAL uses HSIC to measure dependency and optimizes batch size scaling.
result Significant improvements in model accuracy and NLL on image datasets.
Study near-maturity convergence rates of American put prices in Lévy models.
problem Analyzing convergence rates of optimal exercise prices in Lévy models.
method Examined two settings: jumps of unbounded and bounded variation, deriving near-maturity expansions.
result Near-maturity convergence rate of optimal exercise price is of order √(T-t).
Improved bounds on neural network regions using activation histograms.
problem Bounding the number of affine regions in ReLU networks.
method Analysis of algebraic topology problem, extension of framework to subnetwork composition.
result Slightly tighter bounds and insights into parameter initialization.
Brain networks in fMRI are typically identified using spatial independent component analysis (ICA), yet mathematical constraints such as sparse coding and positivity both provide alternate biologically-plausible frameworks for generating brain networks. Non-negative Matrix Factorization (NMF) would suppress negative BO…
Convex neural networks enforce convex constraints on weights and activations, improving generalization.
problem Improving generalization and reducing overfitting in neural networks.
method Enforce convex constraints on weights and activations, using non-negative weights and non-decreasing convex activation functions.
result Convex neural networks self-regularize, outperforming base architectures and achieving similar performance to convolutional architectures.
New activation function BrownianReLU improves LSTM network performance on financial time series.
problem Gradient instability in noisy financial time series data.
method Introduces BrownianReLU, a stochastic activation function based on Brownian motion.
result Significantly improved predictive accuracy and generalization on financial datasets.
Study finds inventory inaccuracies are linked to store activity and product perishability.
problem Inventory record inaccuracy in grocery retailing environments.
method Analysis of 24,000 SKUs across 11 stores, field quasi-experiment on audits.
result Inventory audits can boost sales by 11%, especially for perishable items.
Agent decides when to measure latent states in RL to improve efficiency.
problem Costly state measurement in RL negatively affects future outcomes.
method Introduces AOMDP with measurement action, uses online RL and sequential Monte Carlo.
result Reduced uncertainty improves sample efficiency and policy value.
Active-set algorithm improves Cox regression for shape-restricted covariates.
problem Improving Cox regression for shape-restricted covariates.
method Shape-restricted inference using active-set optimization for spline basis expansion.
result Active-set algorithm produces accurate linear covariate effect estimates.
Few-shot learning is a technique to learn a model with a very small amount of labeled training data by transferring knowledge from relevant tasks. In this paper, we propose a few-shot learning method for wearable sensor based human activity recognition, a technique that seeks high-level human activity knowledge from lo…
In recent years, the Word2Vec model trained with the Negative Sampling loss function has shown state-of-the-art results in a number of machine learning tasks, including language modeling tasks, such as word analogy and word similarity, and in recommendation tasks, through Prod2Vec, an extension that applies to modeling…
Paper develops active learning for clustering unknown pairwise similarities.
problem Learning positive and negative pairwise similarities efficiently.
method Generic active learning framework for correlation clustering.
result Demonstrates effectiveness of query strategies in clustering.
Depth uncertainty networks don't improve with bias correction, contrary to expectations.
problem Improving performance in active learning with overparameterised models like NNs.
method Depth uncertainty networks, compared to underparameterised models, show no improvement in performance with bias correction.
result Depth uncertainty networks do not improve with bias correction, unlike underparameterised models.
Study examines money flow network among firms' accounts in a Japanese region.
problem Understanding the relationship between money flow and economic activities of firms.
method Employed exhaustive bank transfer data, network statistics, Hodge decomposition, and non-negative matrix factorization.
result Identified a 'walnut' structure with core and upstream/downstream components, correlated with economic activities.
In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts with exponentially fewer labeled samples. While previous results show that active…
Human activity recognition plays an important role in people's daily life. However, it is often expensive and time-consuming to acquire sufficient labeled activity data. To solve this problem, transfer learning leverages the labeled samples from the source domain to annotate the target domain which has few or none labe…
In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally balances exploration and exploitation. In practice, however, EEM-based algorithms employ various approximations due to the computational ha…
Non-negative blind source separation (non-negative BSS), which is also referred to as non-negative matrix factorization (NMF), is a very active field in domains as different as astrophysics, audio processing or biomedical signal processing. In this context, the efficient retrieval of the sources requires the use of sig…
Study learns a neuron with non-monotonic activation functions.
problem Learning a single neuron with non-monotonic activation functions.
method Gradient descent (GD) with conditions on activation function and input distribution.
result Learnability of non-monotonic activation functions is established without monotonicity assumption.
We introduce the active exploration problem in Markov decision processes (MDPs). Each state of the MDP is characterized by a random value and the learner should gather samples to estimate the mean value of each state as accurately as possible. Similarly to active exploration in multi-armed bandit (MAB), states may have…
Computational approaches to transcription factor binding site identification have been actively researched for the past decade. Negative examples have long been utilized in de novo motif discovery and have been shown useful in transcription factor binding site search as well. However, understanding of the roles of nega…
We empirically investigate the (negative) expected accuracy as an alternative loss function to cross entropy (negative log likelihood) for classification tasks. Coupled with softmax activation, it has small derivatives over most of its domain, and is therefore hard to optimize. A modified, leaky version is evaluated on…
AReLU uses attention-based rectification to improve neural network performance.
problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.
Deep gated networks help understand training and generalization in deep learning.
problem Understanding the role of SGD in training and generalization of deep neural networks with ReLU activation.
method Developed deep gated networks (DGNs) as a framework to analyze training and generalization in DNNs with ReLU activation.
result Gate adaptation is key for generalization in deep neural networks.
A new model BGAR(1) improves temporal NMF for time series data.
problem Temporal NMF models lack a well-defined stationary distribution.
method Introduced a new Gamma Markov chain model BGAR(1) to overcome the limitation of previous models.
result BGAR(1) model has a well-defined stationary distribution.
The paper analyzes the role of ReLU gates in deep learning networks.
problem Understanding the role of gates in deep learning networks.
method Developed neural path features (NPF) and neural path values (NPV) to characterize the active sub-networks during training.
result The neural path kernel associated with NPFs is a fundamental quantity that characterizes the information stored in the gates of a DNN.
Analysis of log data generated by online educational systems is an essential task to better the educational systems and increase our understanding of how students learn. In this study we investigate previously unseen data from Clio Online, the largest provider of digital learning content for primary schools in Denmark.…
BCD algorithm finds global minima in neural networks.
problem Training deep neural networks to find global minima.
method Block coordinate descent with skip connections and non-negative projection.
result Proves convergence to global minima for strictly monotonic and ReLU activations.
Study finds corruption negatively impacts firm performance.
problem The impact of corruption on firm performance is examined.
method Cross-sectional data analysis of a large international dataset.
result Corruption negatively affects corporate performance.
Generating large quantities of quality labeled data in medical imaging is very time consuming and expensive. The performance of supervised algorithms for various tasks on imaging has improved drastically over the years, however the availability of data to train these algorithms have become one of the main bottlenecks f…
New algorithms speed up learning from large screens of proteins.
problem Lack of scaled data hampers biological machine learning.
method Optimized high throughput screens and generative models.
result Maximized information gain with consistent estimates of p(y∣x). An active margin system for margin loans is proposed for Chinese margin lending market, which uses cash and randomly selected stock as collateral. The conditional probability of negative return(CPNR) after a forced sale of securities from under-margined account in a falling market is used to measure the risk faced by t…
We show how bad and good volatility propagate through forex markets, i.e., we provide evidence for asymmetric volatility connectedness on forex markets. Using high-frequency, intra-day data of the most actively traded currencies over 2007 - 2015 we document the dominating asymmetries in spillovers that are due to bad r…
Active learning recovers choice model from noisy data.
problem Identifying non-parametric choice models from noisy data.
method Directed acyclic graph (DAG) representation and inclusion-exclusion approach.
result Algorithm more accurately recovers frequent preferences.
NegBio-VAE models neural spike counts with negative binomial distribution.
problem Limited biological plausibility of continuous latent variables in VAEs for neural spike modeling.
method Proposes a negative binomial latent-variable model with a dispersion parameter for overdispersed spike count modeling.
result NegBio-VAE outperforms competing models in reconstruction and generation tasks.