This paper extends the convergence rate of DEQs with ReLU to any general activation.
problem Proving global convergence rate for DEQs with general activations.
method Developed a novel population Gram matrix and new form of dual activation with Hermite polynomial expansion.
result Gradient descent converges to a globally optimal solution at a linear rate for DEQs with general activations.
Active learning method balances bias and variance under class imbalance.
problem Active learning under label shift when class proportions differ.
method Mediated Active Learning under Label Shift (MALLS) using a 'medial distribution'.
result MALLS reduces asymptotic sample complexity under arbitrary label shift.
Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the activation, and the weights capture the scale. Here we propose to train the netw…
We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our…
We present a comprehensive study of multilayer neural networks with binary activation, relying on the PAC-Bayesian theory. Our contributions are twofold: (i) we develop an end-to-end framework to train a binary activated deep neural network, (ii) we provide nonvacuous PAC-Bayesian generalization bounds for binary activ…
There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functi…
Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem. Nevertheless, recently it has been shown to be possible to give a non-trivial certified lower bound of minimum adversarial distortion, and some rece…
Complexity measures for neural nets with general activations using path-based norms.
problem Control complexity of neural networks with arbitrary activation functions.
method Approximate general activations with ReLU networks and derive path-based norms for complexity control.
result Preliminary analyses of function spaces and regularized estimators.
Overfitting frequently occurs in deep learning. In this paper, we propose a novel regularization method called Drop-Activation to reduce overfitting and improve generalization. The key idea is to drop nonlinear activation functions by setting them to be identity functions randomly during training time. During testing, …
In theoretical analysis of deep learning, discovering which features of deep learning lead to good performance is an important task. In this paper, using the framework for analyzing the generalization error developed in Suzuki (2018), we derive a fast learning rate for deep neural networks with more general activation …
DAL uses disentanglement for automatic labeling in GAN-based active learning.
problem Reducing human labeling in GAN-based active learning.
method DAL leverages disentanglement in InfoGAN to automatically label datapoints, deciding human labeling based on disagreement with InfoGAN labels and label correction.
result DAL achieves better performance than existing GAN-based active learning approaches on image classification tasks.
Establishes upper bounds on generalization error in active learning.
problem Improving query algorithms in active learning.
method Derives upper bounds on generalization error using informativeness and representativeness query strategies.
result Validates the use of regularization techniques to ensure bounds' validity.
LCW reduces activation shift in neural networks, improving training efficiency and generalization.
problem Activation shift in neural networks leading to non-zero mean preactivation values.
method Linearly constrained weights (LCW) to reduce activation shift in fully connected and convolutional layers.
result LCW resolves the vanishing gradient problem and improves generalization of neural networks.
A new stopping criterion for active learning based on deterministic generalization bounds.
problem Determining the optimal stopping point for active learning when data acquisition is costly.
method The proposed stopping criterion is based on the difference in expected generalization errors and hypothesis testing, derived from PAC-Bayesian theory.
result The proposed stopping criterion effectively stops active learning by combining an upper bound with a statistical test.
New method speeds up neural kernel computations for various activations.
problem Inefficient computation of neural kernels for general activations.
method Fast sketching method using truncated Hermite expansion.
result 106x speedup for approximate CNTK computation on CIFAR-10.
Generative AI predicts economic activity from corporate transcripts.
problem Predicting economic activity using existing measures like surveys.
method Extracted managerial expectations from transcripts using generative AI.
result AI Economy Score predicts economic activity up to 10 quarters ahead.
TransFall uses transfer learning to improve activity recognition from mobile sensors.
problem Performance degradation due to platform and user movement differences.
method Two-tier data transformation, label estimation, and model generation layers.
result TransFall enhances activity recognition accuracy for new scenarios.
New activations improve deep network reproducibility without sacrificing accuracy.
problem Deep networks' reproducibility issues, especially on distributed systems.
method Developed SmeLU activations, smoother than ReLU, to enhance reproducibility.
result SmeLU activations provide better accuracy-reproducibility tradeoffs.
This paper provides an overview of activation functions in neural networks.
problem Confusion in activation function selection and properties in deep learning.
method Analytic review of popular activation functions.
result Clarification of activation function properties and selection.
Paper tackles active labeling for partial supervision.
problem Accessing stochastic gradients with partial supervision.
method Streaming technique to minimize generalization error.
result Proves minimization of generalization error ratio.
Characterizes neural kernel and NNGP for various activations.
problem Understanding neural kernels and NNGP for non-RELU activations.
method Characterization of RKHS for various activation functions.
result Broad class of non-infinitely smooth activations generate equivalent RKHSs at different depths.
Automatically discovers effective activation functions for deep learning.
problem Inconsistent performance of novel activation functions in deep learning networks.
method Evolutionary search for general form, gradient descent for parameters.
result Significant performance improvements over ReLU and other functions.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
problem The choice of activation function affects neural network performance, but ReLU remains dominant.
method Defined a tree-based search space of candidate activation functions and used evolutionary algorithms (mutation, crossover, exhaustive search) to explore and discover better functions.
result Replacing ReLU with evolved activation functions statistically significantly increases network accuracy.
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.
We study the theoretical advantages of active learning over passive learning. Specifically, we prove that, in noise-free classifier learning for VC classes, any passive learning algorithm can be transformed into an active learning algorithm with asymptotically strictly superior label complexity for all nontrivial targe…
Balanced Activation improves object detection performance on long-tailed datasets.
problem Mismatch between training and testing label distributions in object detection.
method Introduces Balanced Activation (Balanced Softmax and Balanced Sigmoid) to address label distribution shift.
result Balanced Activation provides ~3% gain in mAP on LVIS-1.0 compared to state-of-the-art methods.
Early stopping in meta-learning improved by analyzing neural activation patterns.
problem Early stopping in few-shot learning is challenging due to distributional shifts between meta-validation and meta-test sets.
method Activation-Based Early-stopping (ABE) analyzes hidden layer activations from unlabelled support examples to detect when target generalization diverges from source data.
result Simple activation statistics can effectively estimate target generalization, improving few-shot transfer learning across various algorithms and datasets.
Collaborative filtering is a useful technique for exploiting the preference patterns of a group of users to predict the utility of items for the active user. In general, the performance of collaborative filtering depends on the number of rated examples given by the active user. The more the number of rated examples giv…
Generative model predicts daily activity sequences with duration-aware dynamics.
problem Accurately forecasting granular daily activity sequences for energy demand.
method Hierarchical semi-Markov models with duration-aware dynamics.
result Explicitly modeling activity durations improves predictive performance.
Efficiently learns reward functions with fewer queries and shorter computation times.
problem Expensive data generation and labeling in robot learning.
method Batch active preference-based learning methods using determinantal point processes (DPP) and heuristic alternatives.
result Our batch active learning algorithm requires only a few queries and computes them in a short amount of time.
ReLU activations lead to smoother learning curves compared to sigmoidal activations in neural networks.
problem Comparing the performance of ReLU and sigmoidal activations in neural networks.
method Analytical computation of learning curves in shallow networks with different activation functions.
result ReLU networks exhibit continuous transitions in performance, while sigmoidal networks show discontinuous transitions.
Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled. Therefore, the design of effective training methods that…
An appropriate choice of the activation function (like ReLU, sigmoid or swish) plays an important role in the performance of (deep) multilayer perceptrons (MLP) for classification and regression learning. Prototype-based classification learning methods like (generalized) learning vector quantization (GLVQ) are powerful…
Adaptive region-based active learning seeks labels for complex data.
problem Efficiently label complex datasets with minimal human effort.
method Adaptive region partitioning and active learning for distinct predictors.
result Substantial empirical benefits over existing methods.
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. U…
Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We propose in this paper an atomic action-based Bayesian model that const…
Study proposes a stopping criterion for active learning based on error stability.
problem Improving predictive performance in active learning by adaptively annotating samples.
method Proposes a stopping criterion based on error stability for Bayesian active learning.
result Demonstrates the proposed criterion stops active learning at the appropriate timing for various models and datasets.
Active-memory mechanisms can replace self-attention in Transformers, but optimal results often require both.
problem Replacing self-attention with active-memory mechanisms in Transformers.
method Evaluation of various active-memory mechanisms in a Transformer model.
result Active-memory mechanisms can achieve comparable results to self-attention for language modeling, but optimal results are often achieved by combining both mechanisms.
Active learning algorithms propose which unlabeled objects should be queried for their labels to improve a predictive model the most. We study active learners that minimize generalization bounds and uncover relationships between these bounds that lead to an improved approach to active learning. In particular we show th…
Deep learning models outperform classical methods in forecasting neural activity.
problem Improving forecasting of neural activity using deep learning models.
method Systematic evaluation of eight probabilistic deep learning models against classical statistical models and baseline methods.
result Several deep learning models consistently outperform classical approaches in forecasting neural activity.
We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The main algorithms for this problem are {\em{disagreement-based active learning}}, …
Polynomial time algorithm learns depth-2 neural networks with ReLU activations.
problem Learning depth-2 neural networks with non-zero bias terms and general ReLU activations.
method Robust tensor decomposition of Hermite expansions.
result Polynomial time and sample efficient learning of depth-2 networks with ReLU activations.
BatchGFN uses generative flow networks for efficient batch active learning.
problem Efficiently selecting informative batches for active learning.
method Generative flow networks to sample batches proportional to a batch reward.
result Constructs highly informative batches with a single forward pass per point.
Activation functions have a notorious impact on neural networks on both training and testing the models against the desired problem. Currently, the most used activation function is the Rectified Linear Unit (ReLU). This paper introduces a new and novel activation function, closely related with the new activation $Swish…
Personalized activity recognition improves performance for diverse users.
problem Poor performance of impersonal algorithms for individual users.
method Personalized activity recognition using deep embeddings from a fully convolutional neural network with triplet loss.
result Novel subject triplet loss provides the best performance overall.
Deep Neural Networks have been shown to be beneficial for a variety of tasks, in particular allowing for end-to-end learning and reducing the requirement for manual design decisions. However, still many parameters have to be chosen in advance, also raising the need to optimize them. One important, but often ignored sys…
Active-GRPO improves molecular optimization by actively deciding when to imitate or self-improve.
problem Training robust and efficient molecular optimization models with large language models.
method Active-GRPO combines imitation and reinforcement learning, upgrading references and policies dynamically.
result Improves molecular optimization performance, achieving statistically significant gains.
Study shows how activation functions impact the storage capacity of treelike neural networks.
problem Understanding the role of activation functions in neural network expressive power.
method Analysis of treelike two-layer networks with various activation functions in the infinite-width limit.
result Activation functions affect storage capacity and robustness, with nonlinearity increasing capacity and decreasing robustness.