Method learns gestures from touch devices, outperforming state of the art.
problem Automatic gesture recognition on touch devices with multi-user variability.
method Dynamic sampling, convolutional model, recurrent vs. convolutional features.
result Outperforms state of the art on MMG dataset.
User interfaces provide an interactive window between physical and virtual environments. A new concept in the field of human-computer interaction is a soft user interface; a compliant surface that facilitates touch interaction through deformation. Despite the potential of these interfaces, they currently lack a signal …
Federated Learning system for mobile devices.
problem Training models on decentralized data.
method High-level design of a scalable Federated Learning system.
result Solutions to challenges in federated learning.
The study detects and classifies touch gestures with high accuracy.
problem Detecting and classifying touch gestures from touch screens.
method Supervised learning techniques using a capacitive sensor array to record touch and swipe gestures.
result Logistic Regression models achieved over 95% accuracy for all gesture types.
Touch sensing improves grasp prediction accuracy.
problem Predicting grasp outcomes from indirect measurements like vision is challenging.
method Investigated touch sensing's value in multimodal grasping using visuo-tactile deep neural networks.
result Tactile readings significantly improve grasp prediction accuracy.
Designs a Cellular Automata rule for forming touching loop patterns.
problem Forming stable touching loop patterns in a 2D grid.
method Developed a Cellular Automata rule that uses templates to cover the space and match patterns.
result The rule successfully evolves stable touching loop patterns in a 2D grid.
Hand-held system translates foreign menus for diet management.
problem Translation ambiguities and context-specific information for diet management.
method Portable multimedia device, machine translation, context-specific corpora, pre-processing steps, multimedia information.
result Higher accuracy and instant translations compared to Google Translate.
Paper teaches robots to play piano with touch and learning.
problem Teaching robots to play piano with touch and emotion.
method Reinforcement learning from scratch with touch-augmented reward and curriculum.
result Robots can play piano with correct key positions and various requirements.
TACTO simulates high-resolution touch sensing for robotics.
problem Accurate simulation of touch sensing in robotics.
method Fast, flexible, open-source simulator for vision-based tactile sensors.
result Demonstrated TACTO's effectiveness in grasping stability prediction and marble manipulation control.
Proposes a calibration method for various volatility models.
problem Calibrating local-stochastic and path-dependent volatility models to options.
method Generic calibration framework using forward PIDE and particle method.
result Calibration well within market no-touch bid--ask range.
Lipschitz equivalence of self-similar sets is an important area in the study of fractal geometry. It is known that two dust-like self-similar sets with the same contraction ratios are always Lipschitz equivalent. However, when self-similar sets have touching structures the problem of Lipschitz equivalence becomes much …
After the surface theory of Möbius geometry, this study concerns a pair of conformally immersed surfaces in n-sphere. Two new invariants θ and ρ associated with them are introduced as well as the notion of touch and co-touch. This approach is helpful in research about transforms of certain surface classes. As an …
Ghost points affect stability in finite difference schemes for diffusion equations.
problem Impact of ghost points on stability of finite difference schemes.
method Exploration of explicit Euler finite difference scheme with ghost points on diffusion equation.
result Stability of the scheme is affected by ghost points.
Incorrect parity-based descriptions of realizable Gauss diagrams found, but bipartite graphs provide a valid approach.
problem Incorrect descriptions of realizable Gauss diagrams using parity conditions.
method Used bipartite graphs to describe realizable Gauss diagrams.
result Realizable Gauss diagrams can be accurately described using bipartite graphs.
We summarize the main results of our recent investigation of bundles of real Clifford modules and briefly touch on some applications to string theory and supergravity.
Study on elastic curves pinned at the boundary, focusing on minimizers and their interaction with obstacles.
problem Minimizing elastic bending energy for open planar curves with obstacles.
method Investigation of global minimizers and explicit solutions for different values of the penalization parameter.
result Explicit threshold for λ above which minimizers touch the obstacle, regardless of obstacle shape. We study the strong maximum principle for horizontal (p-) mean curvature operator and p-(sub)laplacian operator on subriemannian manifolds including, in particular, Heisenberg groups and Heisenberg cylinders. Under a certain Hormander type condition on vector fields, we show the strong maximum principle holds in higher…
SPIRE enables efficient federated learning for diffusion models by separating client-specific embeddings from a shared backbone.
problem Large diffusion models are impractical for federated learning due to their size.
method SPIRE separates the network into a global backbone and client-specific embeddings, enabling efficient finetuning.
result SPIRE achieves parameter-efficient finetuning, updating only a small fraction of weights.
Non-convex optimization is ubiquitous in machine learning. Majorization-Minimization (MM) is a powerful iterative procedure for optimizing non-convex functions that works by optimizing a sequence of bounds on the function. In MM, the bound at each iteration is required to \emph{touch} the objective function at the opti…
Study of discrete Koenigs nets and their properties.
problem Characterization and properties of discrete Koenigs nets.
method Generalization of inscribed conics to inscribed quadrics and study of Koenigs d-grids.
result Established a bijection between Koenigs d-grids and pairs of discrete autoconjugate curves.
We show that a compact embedded minimal or constant mean curvature annulus with non-vanishing Gaussian curvature which is tangent to two spheres of same radius or tangent to a sphere and meeting a plane in constant contact angle is rotational.
Quantitative structuring is a rigorous framework for the design of financial products. We show how it incorporates traditional investment ideas while supporting a more accurate expression of clients' views. We touch upon adjacent topics regarding the safety of financial derivatives and the role of pricing models in pro…
Double no-touch options, contracts which pay out a fixed amount provided an underlying asset remains within a given interval, are commonly traded, particularly in FX markets. In this work, we establish model-free bounds on the price of these options based on the prices of more liquidly traded options (call and digital …
FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.
problem Inequality in resource allocation hinders participation from resource-constrained devices in federated learning.
method Zero-shot knowledge transfer through a server-assigned distillation process.
result FedZKT effectively transfers knowledge across heterogeneous on-device models without requiring comparable local training efforts.
We prove that an m-dimensional minimal variety in a Riemannian manifold cannot touch the boundary at a point where the sum of the smallest m principal curvatures is greater than 0. We also prove an analogous result for varieties with bounded mean curvature.
New discrete cmc surfaces defined from sphere packings and combinatorics.
problem Creating constant mean curvature surfaces from discrete data.
method Discrete cmc surfaces defined via sphere packings and combinatorial patterns.
result Construction of discrete cmc surfaces from orthogonal ring patterns.
We consider embedded hypersurfaces evolving by fully nonlinear flows in which the normal speed of motion is a homogeneous degree one, concave or convex function of the principal curvatures, and prove a non-collapsing estimate: Precisely, the function which gives the curvature of the largest interior sphere touching the…
On-device federated learning updates edge models by exchanging trained results.
problem Limited training data at edge devices due to model drift.
method OS-ELM for sequential training and autoencoder for anomaly detection, combined with federated learning.
result The proposed approach produces a merged model as accurately as traditional methods with lower costs.
Deep learning identifies unknown IoT devices in network traffic.
problem Unauthorized IoT devices pose security risks in BYOD environments.
method Deep learning applied to network traffic images for IoT device identification.
result Over 99% accuracy in identifying 10 IoT devices and non-white-listed devices.
A method for trust evaluation of devices in human-device coexistence systems.
problem Efficient trust evaluation of devices in systems with diverse physical and social attributes.
method Canonical correlation analysis-enhanced hypergraph self-supervised learning (HSLCCA).
result The proposed HSLCCA method significantly outperforms baseline algorithms in identifying trusted devices.
This summarizes the study of the financial and economic crisis in Europe. The starting questions were: 1) Why do we have a crisis? Unde venis? 2) What will be the outcome? Quo vadis? Here is the reasoning which touches many areas, ranging from financial to politics and from psychology and economy.
Two approaches scale up DNN optimization for diverse edge devices.
problem Optimizing DNNs for edge devices with varying performance requirements.
method Reuse performance predictors on proxy devices and build scalable predictors.
result Optimized DNN designs for many different edge devices without lengthy optimization.
Three configurations of two perpendicular disks in R^3 are examined, the first in which the disks share centers and the other two in which the disks touch at precisely one point. Volume, surface area and mean width calculations dominate the discussion. Integrated mean curvature also appears as an indirect way to comput…
A submanifold M⊂RN is r-neighborly if for any r points in M there is a hyperplane, supporting M and touching it at exactly these r points. We prove that the minimal dimension Δ(k,r) of the Euclidean space, containing a stably r-neighborly submanifold, is asymptotically not smaller than 2kr−k.
The paper proves regularity for varifolds with bounded anisotropic mean curvature.
problem Regularity of varifolds with bounded anisotropic mean curvature.
method Local anisotropic regularity theorem and touching balls approach.
result Varifolds can be covered by countably many C2-regular submanifolds. This paper optimizes how deep learning models are distributed across different devices.
problem Optimizing how large, complex neural networks are split across multiple devices.
method Identified and solved an optimization problem for device placement of DNN operators.
result Automated algorithms that solve the device placement problem for modern pipelined settings.
A system for attributing ad effects using a neural network and Shapley values.
problem Attributing ad effects to individual ads in a complex, sequential environment.
method A two-step approach: response modeling with RNN and credit allocation with Shapley values.
result The system accurately allocates incremental ad effects to individual ads, handling sequence dependence.
Survey on-device ML challenges and future directions.
problem Training machine learning models on-device with limited resources.
method Reformulated as resource constrained learning, comparing techniques from various AI areas.
result Identification of open challenges and future research directions.
Distributed learning adapts to diverse devices, improving performance.
problem Training neural networks on devices with varying capabilities and resources.
method Each device trains a customized neural network, sharing parameters with others.
result Achieves higher rewards on more powerful devices without sacrificing weaker ones.
Flexible device participation improves federated learning convergence.
problem Strict device participation limits federated learning reach.
method Analytical results and new aggregation scheme for flexible participation.
result Convergence improved with flexible device participation.
Paper tackles efficient allocation of multiple devices to users for AutoML services.
problem Allocating multiple devices to multiple users for AutoML services efficiently.
method Develops a multi-device, multi-tenant algorithm for GP-EI, achieving near-linear speedup.
result Achieves near-linear speedup when users are many more than devices.
Synthetic account of Huygens' wave fronts principle.
problem Formalizing Huygens' wave fronts principle.
method Axiomatic/synthetic approach using 'touching' and weak metric notions.
result Simplified exposition of metric spaces and SDG.
We construct a completed version C(Gamma) of the configuration space of a linkage Gamma in R^3 which takes into account the ways one link can touch another. We also describe a simplified version of C(Gamma) which is a blow-up of the space of immersions of Gamma in R^3 A number of simple detailed examples are given.
A real-time context-aware system for IoT using mobile devices.
problem Challenges in running machine learning on mobile devices.
method Developed a context-learning algorithm for mobile devices that updates itself periodically from the server.
result Achieved mean accuracy of 97.51% with only 11ms execution time.
RNNs learn device models from input/output data.
problem Learning complex device models from limited data.
method Empirical study using RNNs to model six different devices.
result RNNs can generate functional software-only models of hardware devices.
Paper optimizes neural architectures for multiple device constraints.
problem NAS ignores device constraints like latency and energy.
method Developed MONAS and DPP-Net for multi-objective optimization.
result Found Pareto-optimal architectures for various devices.
The paper optimizes neural network inference on mobile GPUs.
problem Limited computing power and thermal constraints on mobile CPUs.
method Leverage mobile GPUs for neural network inference.
result Real-time inference of deep neural networks on Android and iOS devices.
New proofs and inequalities for capillarity problems quantify asymmetries.
problem Quantifying asymmetries in capillarity functionals.
method ABP-type technique, symmetrization, selection-type argument.
result Sharp quantitative inequalities for asymmetries in capillarity problems.