MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory an…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “MAC”
Machine Collaborationstat.ML
A new machine learning framework called machine collaboration improves prediction accuracy.
problem Improving prediction accuracy in machine learning.
method Machine Collaboration (MaC) framework, which uses a circular and interactive learning approach.
result Machine Collaboration framework significantly outperforms other state-of-the-art methods in most cases.
Survey on ML for wireless network optimization across PHY, MAC, and network layers.
problem Improving wireless network performance using machine learning.
method Comprehensive review of ML-based techniques for wireless network optimization.
result Machine learning can significantly enhance wireless network QoS and QoE across all layers.
Study on statistical estimation over Gaussian MAC, comparing analog and digital schemes.
problem Distributed minimax statistical estimation over a Gaussian MAC.
method Developed analog joint estimation-communication schemes and derived information-theoretic lower bounds.
result Achieved risk within a logarithmic factor of information-theoretic lower bounds.
Mean Actor Criticstat.ML
We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient of the policy, rather than using only the actions that were actually executed. …
Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraintscs.LG
Paper addresses FL over MAC with DP constraints, proposing a novel consensus scheme.
problem Federated learning over a multiple access channel with differential privacy constraints.
method Proposes a novel consensus scheme using digital distributed stochastic gradient descent (D-DSGD) with artificial noise to preserve DP.
result Demonstrates improved convergence rate and DP level for a given MAC capacity.
In this paper, we consider the joint design of data compression and 802.15.4-based medium access control (MAC) protocol for smartgrids with renewable energy. We study the setting where a number of nodes, each of which comprises electricity load and/or renewable sources, report periodically their injected powers to a da…
MAC combines models without locking them, improving ensemble performance.
problem Improving ensemble learning performance with flexibility.
method Model agnostic combination technique that dynamically combines models.
result MAC outperforms classical methods and competitive to boosting.
DSGD with OAC-MAC scheme achieves better convergence in noisy wireless networks.
problem Performance of decentralized SGD in noisy wireless environments.
method Proposed OAC-MAC scheme for over-the-air computation in DSGD.
result OAC-MAC scheme converges faster with fewer communication rounds.
Paper introduces a modified Allen-Cahn equation for better energy equipartition.
problem Improving energy equipartition in mean curvature flow.
method Developed a modified Allen-Cahn equation (MAC) by time-dependent parameter and Z-transform.
result Improved estimate on discrepancy energy for better equipartition.
Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training. In this paper, we conside…
Edge devices learn a global model collaboratively over wireless channels.
problem Learning a global model from edge devices with imperfect channel state information.
method Proposed analog aggregation scheme, receive beamforming at PS, and convergence analysis.
result Performance improvement with more PS antennas, even with imperfect CSI.
Deep neural networks (DNN) are increasingly being accelerated on application-specific hardware such as the Google TPU designed especially for deep learning. Timing speculation is a promising approach to further increase the energy efficiency of DNN accelerators. Architectural exploration for timing speculation requires…
We consider a distributed learning problem over multiple access channel (MAC) using a large wireless network. The computation is made by the network edge and is based on received data from a large number of distributed nodes which transmit over a noisy fading MAC. The objective function is a sum of the nodes' local los…
Unified derivation of PAC-Bayes and MI bounds for general VC classes with fast rates.
problem Generalization bounds for machine learning models with VC classes.
method Unified derivation of conditional PAC-Bayesian and mutual information bounds, including MAC-Bayesian bounds.
result Nontrivial bounds for general VC classes and faster rates for specific conditions.
The paper shows non-aspherical path components in G2-moduli spaces.
problem Characterizing non-aspherical path components in G2-moduli spaces.
method Using generalised Kummer construction and resolving singularities with Eguchi-Hanson spaces, the authors establish a fibration over each path component with Eilenberg Mac Lane spaces as fibres.
result The comparison map is a fibration over each path component with Eilenberg Mac Lane spaces as fibres, indicating non-trivial families of G2-manifolds.
Motion planning in torimath.GT
Let X be a subcomplex of the standard CW-decomposition of the n-dimensional torus. We exhibit an explicit optimal motion planning algorithm for X. This construction is used to calculate the topological complexity of complements of general position arrangements and Eilenberg-Mac Lane spaces associated to right-angled Ar…
Unified framework sparsifies GNNs for faster inference on large graphs.
problem Space and computational bottlenecks in GNNs due to graph size and connectivity.
method Unified GNN sparsification (UGS) framework that prunes graph adjacency matrix and model weights.
result Graph lottery tickets (GLTs) can be trained in isolation to match full model performance.
An almost-direct product of free groups is an iterated semidirect product of finitely generated free groups in which the action of the constituent free groups on the homology of one another is trivial. We determine the structure of the cohomology ring of such a group. This is used to analyze the topological complexity …
C3 compresses images and videos with low complexity and high performance.
problem High complexity and low performance in neural compression models.
method Overfits a small model to each image or video separately, improving RD performance with low complexity.
result Matches the RD performance of state-of-the-art neural and video codecs with significantly lower decoding complexity.
A new method predicts non-Markovian closure terms for complex systems.
problem Predicting the effect of unresolved variables on resolved dynamics in high-dimensional systems.
method Mamba-Assisted Closure (MAC) framework: sequence model trained to predict closure from resolved trajectory, coupled with reduced-order equations.
result Substantially outperforms existing methods in predictive accuracy and long-time stability.
New RL method MAC improves performance in sparse reward settings.
problem Slow mixing in large state spaces or sparse rewards.
method Multi-level Monte Carlo Actor-Critic (MAC) algorithm.
result Achieves convergence rate comparable to state-of-the-art AC algorithms.
Integrally splits L-spectra of integers into simpler components.
problem Understanding the homotopy type of L-spectra of integers.
method Using Anderson duality and splitting into simpler spectra.
result Splits L-spectra of integers into simpler components.
Abstract sketches historical development of Lie brackets, crossed modules, and Lie-Rinehart algebras.
problem Characterizing and understanding the relationships between Lie brackets, crossed modules, and Lie-Rinehart algebras.
method Historical review and combinatorial group theory considerations.
result The mutual relationship between Lie-Rinehart algebras and Lie brackets, and the historical development of these concepts.
Big data is one of the cornerstones to enabling and training deep neural networks (DNNs). Because of the lack of expertise, to gain benefits from their data, average users have to rely on and upload their private data to big data companies they may not trust. Due to the compliance, legal, or privacy constraints, most u…
In science and engineering, intelligent processing of complex signals such as images, sound or language is often performed by a parameterized hierarchy of nonlinear processing layers, sometimes biologically inspired. Hierarchical systems (or, more generally, nested systems) offer a way to generate complex mappings usin…
We show that for closed orientable manifolds the -dimensional stable systole admits a metric-independent volume bound if and only if there are cohomology classes of degree that generate cohomology in top-degree. Moreover, it turns out that in the nonorientable case such a bound does not exist for stable systoles…
The notion of highly structured ring spectra of prime characteristic is made precise and is studied via the versal examples S//p for prime numbers p. These can be realized as Thom spectra, and therefore relate to other Thom spectra such as the unoriented bordism spectrum MO. We compute the Hochschild and André-Quillen …
New methods for -transform inversion and Wiener-Hopf factorization.
problem Efficient numerical inversion of -transforms and factorization of functions.
method Sinh-deformations of contours, variable changes, and simplified trapezoid rule.
result High precision and speed in evaluating moments and constructing filters.
Many powerful machine learning models are based on the composition of multiple processing layers, such as deep nets, which gives rise to nonconvex objective functions. A general, recent approach to optimise such "nested" functions is the method of auxiliary coordinates (MAC). MAC introduces an auxiliary coordinate for …
Share prices of financial companies from the S&P 500 list have been modeled by a linear function of consumer price indices in the USA. The Johansen and Engle-Granger tests for cointegration both demonstrated the presence of an equilibrium long-term relation between observed and predicted time series. Econometrically, t…
Belief networks are a new, potentially important, class of knowledge-based models. ARCO1, currently under development at the Atlantic Richfield Company (ARCO) and the University of Southern California (USC), is the most advanced reported implementation of these models in a financial forecasting setting. ARCO1's underly…
We introduce the new task of Acoustic Question Answering (AQA) to promote research in acoustic reasoning. The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds. The kind of relational questions …
New probabilistic invariants bound classical topological complexity and category.
problem Bounding classical topological complexity and category.
method Developed probabilistic variants of one-category and diagonal topological complexity.
result Identified new invariants with distributional category and complexity on Eilenberg-Mac Lane spaces.
WMPG reduces policy gradient variance using world models.
problem Reducing variance in policy gradient estimates.
method Trains a world model online to estimate policy gradients and uses imagined trajectories as a baseline.
result WMPG achieves better sample efficiency compared to AC and MAC.
Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks. Many existing methods resort to the stochastic gradient descent algorithm and apply a pre-defined sensitivity to th…
In the last decade, there has been a great technological advance in the infrastructure of mobile technologies. The increase in the use of wireless local area networks and the use of satellite services are also noticed. The high utilization rate of mobile devices for various purposes makes clear the need to track wirele…
We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence thresholds for the intermediate classifiers. As soon as the confidence threshold is met,…
Efficient inverse -transform and pricing barrier and lookback options with discrete monitoringmath.NA
The paper derives formulas for option pricing and random walk expectations.
problem Calculating the price of barrier and lookback options.
method Inverse Z-transform, Fourier/Laplace inversion, Wiener-Hopf factorization, and numerical methods.
result Efficient numerical methods for option pricing are developed.
Develops a graphical calculus for stable curvature invariants.
problem Calculating stable curvature invariants of Riemannian manifolds.
method Graphical calculus based on trivalent graphs with colored edges.
result Derives a curvature identity for compact Einstein manifolds.
The recent success of natural language understanding (NLU) systems has been troubled by results highlighting the failure of these models to generalize in a systematic and robust way. In this work, we introduce a diagnostic benchmark suite, named CLUTRR, to clarify some key issues related to the robustness and systemati…
Neural approximate computing gains enormous energy-efficiency at the cost of tolerable quality-loss. A neural approximator can map the input data to output while a classifier determines whether the input data are safe to approximate with quality guarantee. However, existing works cannot maximize the invocation of the a…
Study improves survival analysis for credit risk by accounting for data drift.
problem Survival analysis in credit risk assumes a stationary data-generating process, but real-world data drift affects model performance.
method Proposes a dynamic joint modelling framework integrating longitudinal behavioural markers and hazard formulations, combined with drift-adaptive techniques.
result Proposed model outperforms classical survival models and drift-adaptive learners in various data drift scenarios.
This paper evaluates debiasing methods on word embeddings to reduce religious bias.
problem Social biases persist in word embeddings, potentially amplifying them in AI applications.
method Investigates and evaluates three multiclass debiasing techniques on three word embeddings.
result ConceptorDebiasing is the most effective method, reducing religious bias by 82-96%.
New method for efficient pricing of double barrier options in Lévy models.
problem Difficulties in accurately and quickly calculating prices of double barrier options in jump models.
method GWR-SINH method based on Gaver-Wynn-Rho acceleration applied to Bromwich integral.
result Accurate and fast calculations of prices of double barrier options in jump models achieved.
In the area of credit risk analytics, current Bankruptcy Prediction Models (BPMs) struggle with (a) the availability of comprehensive and real-world data sets and (b) the presence of extreme class imbalance in the data (i.e., very few samples for the minority class) that degrades the performance of the prediction model…
Compressing DNNs is important for the real-world applications operating on resource-constrained devices. However, we typically observe drastic performance deterioration when changing model size after training is completed. Therefore, retraining is required to resume the performance of the compressed models suitable for…
Resource is an important constraint when deploying Deep Neural Networks (DNNs) on mobile and edge devices. Existing works commonly adopt the cell-based search approach, which limits the flexibility of network patterns in learned cell structures. Moreover, due to the topology-agnostic nature of existing works, including…