SDN mitigates overthinking in deep networks, reducing inference cost and preserving accuracy.
problem Overthinking in deep neural networks, leading to unnecessary computations and misclassifications.
method Introducing internal classifiers (Shallow-Deep Network) to SDNs, enabling early confidence-based exits.
result SDNs reduce inference cost by more than 50% and preserve accuracy, mitigating overthinking.
E 2 ^2 2 CM uses class means for efficient early exits in neural networks.
problem Efficient early exits in neural networks with low computational cost.
method Early Exit Class Means (E 2 ^2 2 CM) based on class means of samples, without gradient-based training. result E 2 ^2 2 CM achieves higher accuracy with fixed training time budget and boosts existing early exit schemes. Enhances early-exit neural networks for anytime classification.
problem Lack of guaranteed prediction quality improvement with longer computation time.
method Post-hoc modification based on Product-of-Experts to enforce conditional monotonicity.
result Achieves conditional monotonicity in prediction quality, enabling anytime classification.
Risk control improves EENNs to make faster predictions without sacrificing accuracy.
problem Determining safe times for EENNs to exit early without degrading performance.
method Adapting risk control frameworks to EENNs to tune their exiting mechanism.
result Risk control enables EENNs to make faster predictions while maintaining user-specified performance goals.
EERO optimizes resource usage for efficient classification.
problem Managing computational resources in complex machine learning models.
method EERO uses multiple classifiers with a reject option to adaptively shorten processing paths.
result EERO effectively manages budget allocation and enhances accuracy in complex scenarios.
The paper accelerates LLM inference by adding early exit heads trained in a self-supervised manner.
problem Inference speed in large language models (LLMs) is slow and resource-intensive.
method Adding self-supervised early exit heads at intermediate transformer layers to stop computation early based on confidence thresholds.
result Entropy provides the most reliable confidence metric for stopping computation early.
EENNs improve inference efficiency but need nested prediction sets for reliable uncertainty estimates.
problem Non-nested prediction sets from standard uncertainty quantification methods in EENNs.
method Introduced anytime-valid confidence sequences (AVCSs) tailored for EENNs.
result AVCSs generate nested prediction sets across EENN exits, addressing the issue of non-nested sets.
This paper introduces early exits in neural networks for faster inference.
problem Reducing inference time and preventing overfitting in neural networks.
method Designing and training multi-output neural networks with early exits.
result Significant reductions in inference time and improved robustness.
ELF improves long-tailed classification by focusing on hard examples.
problem Overfitting to majority classes in long-tailed data distributions.
method EARLY-exiting Framework with auxiliary branches.
result Improves accuracy by more than 3 percent on ImageNet LT and iNaturalist'18.
Energy-efficient DL inference for IoT devices reduces power consumption and improves performance.
problem Energy inefficiency in deep learning models for IoT devices.
method Energy-aware early exiting policy to balance energy consumption and inference accuracy.
result Accuracy and service rate improved up to 25% and 35% respectively.
SIFT reduces training time by selecting samples with approximate losses.
problem Reducing training time by selecting samples with large approximate losses.
method Developed SIFT which uses early exiting to obtain approximate losses with intermediate layer representations for sample selection.
result SIFT achieves significant gains in training time and number of backpropagation steps without optimized implementation.
Confidence-based deferral works well in many scenarios but fails in specific cases.
problem Understanding when confidence-based deferral fails and when other strategies are better.
method Theoretical analysis and post-hoc deferral mechanisms were studied.
result Theoretical analysis characterizes settings where confidence-based deferral may fail.
Confidence-based filtering reveals latent structure in diffusion models.
problem Unclear latent structure in diffusion models.
method Confidence scores from a classifier.
result Class-relevant latent structure emerges under confidence-based filtering.
A hybrid neural network optimizes AI deployment on edge and cloud for energy efficiency.
problem Energy and resource constraints in edge devices for deep learning models.
method Conditionally deep hybrid neural network with quantized layers at edge and full-precision layers at cloud.
result Early classification at the edge reduces energy consumption by 5.5x on CIFAR-10 dataset.
Entropy-based decoding improves DLM sampling efficiency.
problem Decoding strategy challenges in flexible DLMs.
method Entropy sum-based confidence-based decoding.
result Entropy sum-based decoding achieves ε \varepsilon ε -accuracy with O ~ ( H ( X 0 ) / ε ) \widetilde O(H(X_0)/\varepsilon) O ( H ( X 0 ) / ε ) iterations. Ensembling multiple predictions is a widely used technique for improving the accuracy of various machine learning tasks. One obvious drawback of ensembling is its higher execution cost during inference. In this paper, we first describe our insights on the relationship between the probability of prediction and the effec…
We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes that adaptively utilize networks. We first pose an adaptive network evaluation sc…
This paper improves self-play learning in games by manipulating experience distributions.
problem Improving self-play learning in games through better experience sampling.
method Three approaches: weighted sampling, Prioritized Experience Replay, and diversifying trajectories.
result Major improvements in early training performance in some games, minor improvements overall.
The study clusters neighborhoods based on childhood vulnerability data and program retention rates.
problem Improving childhood outcomes and decision-making in early childhood development.
method Data-driven approaches combining public and private sources to visualize children's experiences and analyze program retention rates.
result Neighborhoods can be clustered based on childhood vulnerability, and certain programs have higher retention rates.
Deep RL model optimizes pedestrian evacuation in multi-exit scenarios.
problem Optimizing pedestrian evacuation in multi-exit indoor environments.
method MultiExit-DRL using Deep Reinforcement Learning with DQN and DNN.
result MultiExit-DRL reduces evacuation frames and optimizes exit utilization.
Study of a generalized geometric Brownian motion with varying entry and exit rates.
problem Understanding the long-run behavior of economic systems with growth, volatility, entry, and exit.
method Generalized geometric Brownian motion framework with varying entry and exit rates, analyzing moments and survival probability.
result Optimal exit rate minimizes mean first-passage time, influencing system outcome.
Analyzes first exit times in a modified Barndorff-Nielsen and Shephard model.
problem Analyzing first exit times in a modified Barndorff-Nielsen and Shephard model.
method Formulated an approximate model driven by Brownian motion and Lévy subordinator, analyzed first exit times of log-return process.
result First exit time process decomposes into Brownian motion and Lévy subordinator components.
Study uses LLMs to optimize VC exit timing after IPO.
problem Optimal exit timing after IPO is crucial but not well studied.
method Uses LLMs to analyze financial data and market signals.
result LLMs can improve VC exit timing and generate better returns.
A method for generating future samples in auto-regressive processes using confidence-based sampling.
problem Generating future samples in auto-regressive processes efficiently and accurately.
method Confidence-based sampling to simplify and parallelize the auto-regressive generation process.
result The method successfully captures complex data structures and generates meaningful future samples with lower computational cost.
Study examines strategic exit timing in uncertain competition.
problem Timing of strategic exit decisions in competitive markets with uncertainty.
method Constructs a stochastic game equilibrium for exit strategies involving state variable and posterior belief process.
result Unique equilibrium found for symmetric Bayesian players.
Proposes a new method for probabilistic regression in computer vision.
problem Lack of natural probabilistic meaning in confidence-based regression.
method Energy-based model of conditional target density using deep neural network.
result 2.2% AP improvement over Faster-RCNN for object detection on COCO dataset.
Enhances KANs for accuracy and interpretability with multi-exit architecture.
problem Unclear optimal depth for KANs and difficulty in optimization and interpretation.
method Introduces multi-exit KANs with each layer having its own prediction branch.
result Multi-exit KANs outperform single-exit versions on various datasets.
This research examines relationship between staging of Venture Capital (VC) investments and social feedback visible in publicly available data on the Web. We address the question of Venture Capital investment sensitivity to performance and prospects of new venture, given as likelihood of obtaining future financing, ava…
This work optimizes DNN inference for energy-harvesting devices by compressing and selectively executing neural network exits.
problem Inference delays and energy inefficiency in energy-harvesting devices.
method Developed a power trace-aware and exit-guided network compression algorithm for multi-exit neural networks.
result Superior accuracy and reduced latency compared to state-of-the-art techniques.
Paper uses EXIT analysis for community detection with side information.
problem Community detection in the presence of side information.
method Imported EXIT method from iterative decoding of error control codes.
result Predicts asymptotic phase transition and residual errors for community detection.
New method controls mean exit time in stochastic systems using machine learning and quasipotential.
problem Controlling mean exit time in stochastic dynamical systems with white noise.
method Developed a neural network to compute the quasipotential function and designed an algorithm to calculate the controller.
result Effective and accurate control strategy demonstrated through numerical experiments.
Previous work in hierarchical reinforcement learning has faced a dilemma: either ignore the values of different possible exit states from a subroutine, thereby risking suboptimal behavior, or represent those values explicitly thereby incurring a possibly large representation cost because exit values refer to nonlocal a…
Unified ML approach for SDEs in bounded domains.
problem Challenges in simulating SDEs with particle exit phenomena.
method Hybrid approach combining diffusion model and exit prediction network.
result Accurate modeling of interior dynamics and boundary interactions.
Paper analyzes venture capital exit decisions under inconsistent preferences.
problem Time-inconsistent preferences in venture capital exit timing.
method Modeling four types of venture capitalists with varying levels of inconsistency.
result Time-inconsistent venture capitalists exit earlier than consistent ones.
Based on Markvorsen and Palmer's work on mean time exit and isoperimetric inequalities we establish slightly better isoperimetric inequalities and mean time exit estimates for minimal submanifolds of N × R N\times\mathbb{R} N × R . We also prove isoperimetric inequalities for submanifolds of Hadamard spaces with tamed second fund…
Developed policy gradient methods for stochastic control with exit time, outperforming traditional techniques in share repurchase pricing.
problem Optimal control with exit time in stochastic models.
method Two types of algorithms: direct policy learning and alternately learning value function and control.
result Policy gradient methods outperform PDE or neural networks in share repurchase pricing.
The purpose of this article is to compute the expected first exit times of Brownian motion from a variety of domains in the Euclidean plane and in the hyperbolic plane.
We prove explicit upper and lower bounds for the L 1 L^1 L 1 -moment spectra for the Brownian motion exit time from extrinsic metric balls of submanifolds P m P^m P m in ambient Riemannian spaces N n N^{n} N n . We assume that P P P and N N N both have controlled radial curvatures (mean curvature and sectional curvature, respectively) as view…
AdaEnsemble learns adaptive feature interactions for CTR prediction.
problem Learning feature interactions for CTR prediction in recommender systems and Ads ranking.
method AdaEnsemble is a Sparsely-Gated Mixture-of-Experts (SparseMoE) architecture that dynamically selects feature interaction depth.
result AdaEnsemble achieves better prediction accuracy and inference efficiency compared to state-of-the-art models.
Eigenfunctions constructed via Brownian motion exit times on curved spaces.
problem Constructing eigenfunctions of Laplacian on curved spaces.
method Using exit times of Brownian motion on a Riemannian manifold.
result Eigenfunctions can be constructed for a wide range of Laplacian eigenvalues.
AdaPID optimizes diffusion-based samplers by dynamically adjusting schedules.
problem Optimizing the intermediate-time dynamics in diffusion-based samplers.
method Develops a time-varying stiffness schedule using Piece-Wise-Constant (PWC) parametrizations and a hierarchical refinement approach.
result QoS-driven PWC schedules consistently improve sampling fidelity and accuracy.
CAdam optimizes online learning by adapting to distribution shifts and noise.
problem Challenges in online learning data, including distribution shifts and noise, affect Adam's performance.
method CAdam uses a confidence-based approach to assess the consistency between momentum and gradients before updating parameters.
result CAdam outperforms other optimizers in various settings with distribution shift or noise.
Study shows submanifolds can't be immersed in certain spaces.
problem Non-immersibility of submanifolds with infinite mean exit time.
method Not based on the weak maximum principle at infinity, generalizes previous results.
result Estimates for complete tower of moments for submanifolds with small mean curvature.
Investors optimize liquid staking decisions in LSP and AMM protocols.
problem Optimal timing and allocation in liquid staking protocols.
method Derive optimal allocation strategy and model optimal exit timing using Laplace transforms and free-boundary techniques.
result Optimal stop-loss strategy maximizes expected payoff, influenced by fees and opportunity gains.
This paper investigates sufficient conditions for a Feynman-Kac functional up to an exit time to be the generalized viscosity solution of a Dirichlet problem. The key ingredient is to find out the continuity of exit operator under Skorokhod topology, which reveals the intrinsic connection between overfitting Dirichlet …
Mean exit times concentrate near equators and minimal hypersurfaces in high dimensions.
problem Understanding mean exit times on spheres and manifolds.
method Analyzing Brownian motion on spheres and manifolds with minimal hypersurfaces.
result Mean exit times concentrate near equators and minimal hypersurfaces in high dimensions.
Model predicts exit of private companies using voting of three classifiers.
problem Predicting the exit of privately held companies from limited data.
method Combines three classifiers (Logistic Regression, Random Forest, SVM) on extracted data.
result Achieves 63% predictive accuracy for Private Equity investors.
Efficiently solves exploration-exploitation in LQR using Lagrangian relaxation.
problem Exploration-exploitation dilemma in linear quadratic regulator (LQR) setting.
method Relax optimistic optimization into a constrained extended LQR problem, then solve using Riccati equations.
result Computes ε ε ε -optimistic controller efficiently with O ( log ( 1 / ε ) ) O\big(\log(1/ε)\big) O ( log ( 1/ ε ) ) Riccati equations.