Enhances neural network dynamics to boost computational capacity.
problem Improving computational capacity of neural networks.
method Introducing Phase Transition Adaptation to drive system dynamics towards edge of stability.
result Consistently achieves enhancement in computational capacity over multiple datasets.
Infinite VAE adapts to data with Dirichlet process for semi-supervised learning.
problem Handling limited labeled data in semi-supervised learning.
method Infinite VAE with Dirichlet process for automatic model capacity adaptation.
result The method automatically varies the number of autoencoders based on data.
Adaptive Divergence speeds up AO for heavy generators.
problem Training high-capacity models on generators is computationally expensive.
method Introduces a novel family of divergences that vary model capacity.
result Significant acceleration in AO tasks with reduced computational costs.
Full-capacity uRNNs improve performance over restricted-capacity ones.
problem Vanishing and exploding gradient issues in recurrent neural networks.
method Optimized full-capacity unitary recurrence matrices over all unitary matrices.
result Significantly improved performance compared to LSTMs and restricted-capacity uRNNs.
This research investigates selectively pruning hyper and hypo neurons to improve neural network generalization.
problem Improving neural network generalization to unseen data.
method Investigates pruning hyper and hypo neurons selectively in fully connected layers of CNNs.
result Selective pruning of hyper and hypo neurons improves model performance on out-of-domain data.
gLSTM improves graph neural networks by increasing storage capacity to prevent over-squashing.
problem Over-squashing in GNNs collapses information from a large receptive field into a single vector, creating an information bottleneck.
method Introduced a new synthetic task to measure over-squashing and adapted ideas from sequence modeling to develop gLSTM, a novel GNN architecture with improved capacity.
result gLSTM architecture demonstrates strong performance on synthetic and real-world graph benchmarks, mitigating over-squashing.
Self-adaptive training improves deep learning robustness.
problem Improving deep learning performance on corrupted data.
method Dynamic correction of problematic labels using model predictions.
result Self-adaptive training significantly improves generalization over ERM under various levels of noise.
Wide neural networks can degrade performance, contrary to conventional wisdom.
problem Understanding the limitations of increasing network width in neural networks.
method Using Deep Gaussian Processes to decouple capacity and width, analyzing their effects on representational power and non-Gaussianity.
result Wide neural networks can become less adaptable and more Gaussian, leading to performance degradation.
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
SpaceNet improves continual learning by intelligently compressing neural connections.
problem Catastrophic forgetting in sequential learning tasks.
method SpaceNet trains sparse deep neural networks adaptively, compressing task-specific connections.
result SpaceNet outperforms existing methods in class incremental learning scenarios.
Graph neural networks struggle to distinguish certain graph structures.
problem Difficulty in distinguishing graphs with graph neural networks.
method Analysis of communication capacity in message-passing model of graph neural networks.
result Capacity of MPNN needs to grow linearly for trees and quadratically for general connected graphs.
Optimal hidden-target learning for online inventory optimization on general convex sets.
problem Online inventory optimization (OIO) on arbitrary bounded convex capacity sets.
method Maintaining a hidden target and projecting it onto the feasible order-up-to set.
result The method improves the best known regret guarantee for OIO on general convex sets from inverse to inverse-square-root dependence on the common-demand probability.
Adaptive personalized federated learning improves local model personalization.
problem Maximizing global model performance limits local model personalization.
method APFL algorithm trains local models while contributing to global model, with optimal mixing parameter and communication-efficient optimization.
result Demonstrates effectiveness of personalization schema and correctness of generalization theories.
The study examines how alternative resource adequacy contract designs affect market participants' risk profiles and resource mix.
problem The tension between promoting reliability and competition in liberalized electricity markets.
method Constructs a stochastic equilibrium model of a competitive market with incomplete risk trading and computes investment equilibria under different contracting regimes.
result Alternative contracting regimes can induce different risk profiles and resource mixes, affecting market outcomes.
Two-layer neural networks learn features through a few gradient descent steps, improving approximation capacity.
problem Improving approximation capacity of two-layer neural networks.
method Theoretical investigation of a two-layer neural network's adaptation to target function through a few gradient descent steps.
result Learning multiple target directions requires a larger batch size and more gradient steps, improving approximation capacity.
New learning rates derived for Tikhonov-regularized problems without kernel assumptions.
problem Learning rates for Tikhonov-regularized learning problems.
method Minimax adaptive rates derived using Fourier isocapacitary condition and interpolation theory.
result Derivation of minimax adaptive rates without requiring kernel assumptions.
Graph neural networks optimize radio resource management policies for wireless networks.
problem Optimizing user selection and power control in wireless networks with fairness constraints.
method Formulated as a Lagrangian dual problem, RRM policies are parameterized by a GNN architecture trained on channel conditions.
result The method achieves superior tradeoff between average and 5th percentile rates, demonstrating fairness.
Meta-learning algorithms can negatively adapt, reducing performance on diverse tasks.
problem The negative impact of adaptation in meta-learning algorithms on diverse tasks.
method Investigated the effects of adaptation in MAML (Model-Agnostic Meta-Learning) on a range of meta-training tasks.
result Adaptation in MAML can significantly decrease performance on a range of tasks.
Adaptive RNN using mixture layer for multi-pattern sequences.
problem Inadequate RNN performance on sequences with multiple patterns.
method Introducing a mixture layer to partition and store prototype vectors, enabling adaptive state updates.
result M-RNN outperforms traditional RNN in assimilating sequences with multiple patterns.
DNPUs improve neural network performance with high-capacity nanoelectronic nodes.
problem Limited performance of single DNPUs in solving complex classification problems.
method Developed DNPUs as high-capacity neurons and implemented multi-DNPU networks.
result Feed-forward DNPU networks improve single DNPU performance from 77% to 94% test accuracy.
The paper addresses adversarial robustness in in-context learning models.
problem Adversarial distribution shifts threaten the reliability of in-context learning models.
method A distributionally robust meta-learning framework is introduced to provide worst-case performance guarantees under Wasserstein-based distribution shifts.
result Model robustness scales with the square root of its capacity and is penalized by the square of the perturbation magnitude.
Dynamic residual adapters improve performance across multiple latent domains without domain labels.
problem Overfitting to large domains and ignoring smaller ones in multi-domain learning.
method Dynamic residual adapters and augmentation strategies inspired by style transfer.
result Dynamic residual adapters significantly outperform standard models on multiple latent domains.
The paper examines Adaptive Lasso and Transfer Lasso, highlighting their differences and proposing a new method.
problem Comparing and contrasting Adaptive Lasso and Transfer Lasso.
method Theoretical analysis of asymptotic properties and introduction of a new method.
result The Transfer Lasso method reduces non-asymptotic estimation errors compared to Adaptive Lasso.
The paper introduces a new geometric capacity and proves inequalities related to it.
problem Developing a new geometric capacity and comparing it to classical quantities.
method Introducing the general p-affine capacity and proving its properties and inequalities. result Sharp geometric inequalities for the general p-affine capacity are derived. Unbalanced minibatch Optimal Transport improves domain adaptation performance.
problem Optimal transport distances are computationally expensive for large datasets.
method Use unbalanced minibatch Optimal Transport to estimate distances over subsets of data.
result Unbalanced Optimal Transport leads to better domain adaptation results.
New affine BV-capacity differs from classic in higher dimensions.
problem Classic BV-capacity limitations in higher dimensions.
method Geometric-measure-theoretic study of affine BV-capacity.
result Affine BV-capacity is distinct from classic in higher dimensions.
Theoretical study on using optimal transport for domain adaptation.
problem Improving efficiency of machine learning algorithms in domain adaptation.
method Theoretical analysis of optimal transport theory applied to three DA settings.
result Wasserstein metric provides generalization guarantees for DA.
Study on sparsity in CNNs trained with adaptive methods.
problem Understanding and optimizing sparsity in CNNs trained with adaptive methods.
method Experimental study of filter level sparsity in CNNs with BN and ReLU, using adaptive gradient descent and L2 regularization.
result Implicit sparsity can improve CNN performance and speedup without modifications.
We study various capacities on compact Kähler manifolds which generalize the Bedford-Taylor Monge-Ampère capacity. We then use these capacities to study the existence and the regularity of solutions of complex Monge-Ampère equations.
Constructs G-equivariant symplectic capacities for Lie groups and studies their continuity.
problem Defining and studying symplectic capacities for Lie groups.
method Constructs G-equivariant symplectic capacities for Lie groups G and studies their continuity. result Shows that these capacities are invariants of integrable systems.
Solves a discrete logarithmic Minkowski problem for electrostatic p-capacity.
problem Characterize measures generated by electrostatic p-capacity.
method Solves the discrete logarithmic Minkowski problem for 1 < p < n.
result Solves the discrete logarithmic Minkowski problem for measures in general position.
Proves existence and uniqueness of solutions to Lp Minkowski problem for electrostatic p-capacity.
problem Existence and uniqueness of solutions to Lp Minkowski problem for electrostatic p-capacity.
method Proved existence and uniqueness of solutions for specific ranges of p and p-capacity.
result Proves existence and uniqueness of solutions for Lp Minkowski problem for electrostatic p-capacity.
Infinite mixture prototypes adapt to complex data for few-shot learning.
problem Few-shot learning with complex data distributions.
method Adaptive representation of classes by clusters, inferring cluster number.
result 25% absolute accuracy improvement on alphabets, state-of-the-art semi-supervised clustering.
CapOptix uses options theory to price capacity in electricity markets.
problem Traditional capacity market designs fail to account for risk and price shocks.
method Interprets capacity commitments as reliability options and uses Markov Regime Switching Process.
result CapOptix provides more accurate pricing of capacity premia compared to existing mechanisms.
A new memory system handles non-stationary environments by self-sizing and retaining memories.
problem Non-stationary environments where memories arrive over time and must be distinguished from noise.
method A self-sizing continual associative memory that generalizes Hopfield's network, handling adaptation and novelty.
result The memory system grows to the intrinsic memory demand of the environment and retains memories without forgetting.
Extends capacity analysis to neural networks, showing how capacity is distributed across layers.
problem How capacity is distributed in neural networks with non-linear layers.
method Introduces layer decoupling to quantify non-linear activation's impact, and uses a markovian rule for capacity propagation in deep networks.
result Shows that under certain conditions, capacity allocation in neural networks is equivalent to linear capacity allocation in an extended input space.
Paper develops a hybrid DNN approach for RUL prediction with adaptive drift.
problem RUL estimation challenges in practice, especially online update and uncertainty quantification.
method Hybrid DNN approach with Wiener-based-degradation model and adaptive drift. LSTM-CNN for trajectory prediction and Bayesian inference for adaptive drift.
result Superior accuracy in RUL prediction demonstrated on turbofan engines data.
While symplectic manifolds have no local invariants, they do admit many global numerical invariants. Prominent among them are the so-called symplectic capacities. Different capacities are defined in different ways, and so relations between capacities often lead to surprising relations between different aspects of sympl…
Study excess capacity in neural networks using Rademacher complexity.
problem Understanding how much capacity deep networks have beyond what's needed for classification.
method Unified Rademacher complexity bounds for function composition and convolutional layers, considering Lipschitz constants and initialization norms.
result There is substantial excess capacity per task, and capacity can be kept similar across different tasks.
RL platform enhances user journeys in healthcare apps.
problem Improving user experience and personalization in healthcare apps.
method Reinforcement learning framework for adaptive interventions.
result Significant increase in basket size through personalized recommendations.
Study rigidity by logarithmic capacity and related functions.
problem Rigidity phenomena in kernel functions and capacities.
method Exploration of Bergman kernel, logarithmic capacity, Green's function, and Euclidean distance/volume.
result Established rigidity theorems by logarithmic capacity.
Study binary perceptrons' capacity using random duality theory.
problem Characterize the capacity of binary perceptrons with general thresholds.
method Utilized fully lifted random duality theory (fl RDT) to characterize the capacity.
result Characterizations match replica symmetry breaking predictions and uncover the capacity for zero-threshold scenario.
Extends recommender methods to respect capacity constraints.
problem Recommendation under capacity constraints in various settings.
method Extend three state-of-the-art latent factor recommendation approaches (PMF, GeoMF, BPR) to optimize for both recommendation accuracy and expected item usage that respects capacity constraints.
result Experimental results highlight the benefit of the method for recommendation under capacity constraints.
Mobile apps and machine learning improve malaria prevention and treatment.
problem High malaria cases and deaths in low-income countries.
method Adaptive interventions using mobile health apps and machine learning.
result Increased malaria testing, adherence, and provider skills.
Study capacity constraints in continual learning with a simple model.
problem Understanding optimal resource allocation for agents with limited memory and compute resources.
method Analyzes a capacity-constrained linear-quadratic-Gaussian (LQG) sequential prediction problem and demonstrates optimal capacity allocation strategies.
result Derives a solution to the capacity-constrained LQG sequential prediction problem and shows how to optimally allocate capacity across sub-problems in the steady state.
New complete panel dataset for LMICs helps analyze innovation and development.
problem Lack of complete data for empirical analyses in LMICs.
method Predictive Mean Matching multiple imputation technique.
result Created a large dataset of 47 variables for 82 LMICs from 2005-2019.
The paper provides theoretical insights into deep domain adaptation.
problem Closing the gap between source and target domains in deep domain adaptation.
method A rigorous framework to explain transfer learning and minimize loss.
result First theoretical result characterizing joint space and transfer learning gain.
Upper bounds for Lagrangian capacities of Liouville domains
problem Lagrangian capacity of Liouville domains
method Using S1-equivariant techniques result Extremal Lagrangian torus on the boundary of ellipsoid