Deep-Lock secures DNN models with secret keys.
problem Preventing unauthorized usage of DNN models.
method Uses S-Boxes and key scheduling to encrypt DNN parameters.
result Ensures correct functioning only with the correct secret key.
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Model Locking”
ESOP uses Bayesian optimization to find optimal lock-down schedules.
problem Finding optimal lock-down schedules balancing health and economy.
method Bayesian optimization interacting with epidemiological models.
result ESOP schedules balance public health and economic impacts.
Lock-in, the escalating commitment of decision-makers to an ineffective course of action, has the potential to explain the large cost overruns in large scale transportation infrastructure projects. Lock-in can occur both at the decision-making level (before the decision to build) and at the project level (after the dec…
Study on bit threads and their locking properties in holographic spacetimes.
problem Understanding the conditions under which regions can be locked in holographic spacetimes.
method Investigation of different density bounds and their implications on the locking of regions.
result Non-crossing regions can be locked under the most stringent bound, but crossing regions cannot.
Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward locking, backward locking, and update locking problems. Existing solutions for a…
Several experimental studies claim to be able to predict the outcome of simple decisions from brain signals measured before subjects are aware of their decision. Often, these studies use multivariate pattern recognition methods with the underlying assumption that the ability to classify the brain signal is equivalent t…
Due to space limitations, our submission "Source Separation and Clustering of Phase-Locked Subspaces", accepted for publication on the IEEE Transactions on Neural Networks in 2011, presented some results without proof. Those proofs are provided in this paper.
New methods combine model predictions to avoid linear mixtures' limitations.
problem Combining predictions from different models to avoid linear mixtures' limitations.
method Log-linear pooling (locking) and quantum superposition (quacking) to optimise model weights.
result Demonstrated locking method with illustrative example and practical application.
Study finds TVL doesn't predict cryptocurrency returns.
problem Assumption of TVL predicting returns in crypto markets.
method Examined TVL-sorted portfolios against crypto market returns, using various TVL measures.
result TVL-sorted portfolios' returns are linear functions of crypto market returns, replicable with standard tools.
Study on TVL computation in DeFi protocols, proposing verifiable metrics.
problem Lack of standardization and verifiability in TVL computation.
method Systematic study of 939 DeFi projects, analyzing methodologies and proposing vTVL.
result 240 protocols use repeated balance queries, limiting verifiability.
Paper tackles dynamic behavior of variable topology mechanisms, presenting new transition conditions.
problem Dynamic behavior of mechanisms with changing kinematic topology.
method Presented new transition conditions for variable topology mechanisms using projected motion equations and Voronets equations.
result Results show the dynamic behavior of joint locking in 3R and 6DOF mechanisms.
Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully l…
Accelerates optimization in asynchronous systems with sparse updates.
problem Optimizing finite-sum objectives in asynchronous lock-free environments.
method New accelerated SVRG variant with sparse updates.
result Achieves optimal incremental gradient complexity.
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.
Stochastic gradient descent~(SGD) and its variants have attracted much attention in machine learning due to their efficiency and effectiveness for optimization. To handle large-scale problems, researchers have recently proposed several lock-free strategy based parallel SGD~(LF-PSGD) methods for multi-core systems. Howe…
Flattening the curves: on-off lock-down strategies for COVID-19 with an application to Braziq-bio.PE
This study analyzes the effects of lifting lockdowns on Brazil's COVID-19 spread.
problem Understanding the impact of lifting lockdowns on Brazil's COVID-19 spread.
method Extended SEIR model with on/off strategy and developed a neural regressor.
result Lifting lockdowns could lead to a more severe second wave of COVID-19.
Study factors affecting liquidity on decentralized exchanges, introducing new metrics.
problem Understanding and predicting liquidity on decentralized exchanges (DEXs).
method Analyzes platform, blockchain, token pair, and liquidity pool factors; introduces new metrics.
result Identifies how various factors affect liquidity through concentration and total value locked.
While the backpropagation of error algorithm enables deep neural network training, it implies (i) bidirectional synaptic weight transport and (ii) update locking until the forward and backward passes are completed. Not only do these constraints preclude biological plausibility, but they also hinder the development of l…
Proves Riemannian positive mass theorem with singularities.
problem Proves Riemannian positive mass theorem for specific types of singular manifolds.
method Uses initial data sets with a second fundamental form to transfer convexity between different singularity components.
result Proves the theorem for manifolds with some mean-concave components and others mean-convex.
Neuroscientists have enjoyed much success in understanding brain functions by constructing brain connectivity networks using data collected under highly controlled experimental settings. However, these experimental settings bear little resemblance to our real-life experience in day-to-day interactions with the surround…
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. CYCLADES is asynchronous during shared model updates, and requires no memory locking mechanisms, similar to HOGWILD!-type algorithms. Unlike HOGWILD!, CYCLADES introduces no conflicts during the par…
Exchanges acquire excess processing capacity to accommodate trading activity surges associated with zero-sum high-frequency trader (HFT) "duels." The idle capacity's opportunity cost is an externality of low-latency trading. We build a model of decentralized exchanges (DEX) with flexible capacity. On DEX, HFTs acquire …
Backpropagation (BP) is the cornerstone of today's deep learning algorithms, but it is inefficient partially because of backward locking, which means updating the weights of one layer locks the weight updates in the other layers. Consequently, it is challenging to apply parallel computing or a pipeline structure to upd…
Synchronization in a market model with time delaysphysics.soc-ph
Study on synchronization in financial markets with time delays.
problem Understanding market dynamics and synchronization in financial systems with time delays.
method Examined a system of coupled non-linear delay-differential equations, linearized for small delays, and analyzed collective dynamics using bifurcation diagrams and numerical solutions.
result Demonstrated that limit cycles can be maintained in coupled N-asset models with appropriate parameterization, leading to market synchronization.
OOM-RL uses financial market losses to align AI agents in autonomous systems.
problem Constrained alignment of autonomous software agents in live financial markets.
method Deploying agents in live financial markets to enforce strict test-driven workflows.
result Final OOM-RL-aligned system achieved a stable equilibrium with an annualized Sharpe ratio of 2.06.
Social and individual learning in the Minority Gamephysics.soc-ph
Social learning can make financial markets inefficient, but individual learning can fix this.
problem Inefficiencies in financial markets due to social learning.
method Study of the Minority Game model with social and individual learning mechanisms.
result Individual learning can rescue a population from the inefficiencies caused by social learning.
Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model …
In this paper we introduce two models of opinion dynamics in oligopoly markets and apply them to a situation, where a new entrant challenges two incumbents of the same size. The models differ in the way the two forces influencing consumer choice -- (local) social interactions and (global) advertising -- interact. We st…
Priority to unemployed immigrants? A causal machine learning evaluation of training in Belgiumecon.EM
Based on administrative data of unemployed in Belgium, we estimate the labour market effects of three training programmes at various aggregation levels using Modified Causal Forests, a causal machine learning estimator. While all programmes have positive effects after the lock-in period, we find substantial heterogenei…
We show that the bordism group of closed 3-manifolds with positive scalar curvature (psc) metrics is trivial by explicit methods. Our constructions are derived from scalar-flat K{ä}hler ALE surfaces discovered by Lock-Viaclovsky. Next, we study psc 4-manifolds with metric singularities along points and embedded circles…
Study predicts success of crypto-tokens on Pump.fun platform.
problem Identify factors affecting the success of new crypto-tokens.
method Build predictive models using bonding curve mechanism and structural/behavioral variables.
result Conditional variables significantly improve the predictive power of token success.
KLD token adjusts supply based on macroeconomic debt index, creating deflationary effect.
problem Managing deflationary pressures in digital assets.
method Debt-indexed supply adjustments linked to macroeconomic data.
result Deflationary mechanism strengthens as debt rises.
Hidden Markov Model helps track asymptomatic carriers in pandemic.
problem Tracking spread of asymptomatic carriers (super-spreaders) during pandemic.
method Applied Hidden Markov Model to analyze COVID-19 data.
result Better assessment of spread extent for calibrated interventions.
A new method uses conformal prediction to create reliable confidence masks for image super-resolution.
problem Uncertainty quantification in image super-resolution using generative models.
method Conformal prediction techniques applied to a confidence mask for reliable uncertainty communication.
result Strong theoretical guarantees and empirical solid performance in image super-resolution.
We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks. The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates exploding and vanishing gradients, resulting in the ability…
Extending methods first used by Casson, we show how to verify a hyperbolic structure on a finite triangulation of a closed 3-manifold using interval arithmetic methods. A key ingredient is a new theoretical result (akin to a theorem by Neumann-Zagier and Moser for ideal triangulations upon which HIKMOT is based) showin…
Deep Learning Meets SAReess.IV
Deep learning applied to SAR data is explored in this paper.
problem Limited use of deep learning in SAR data processing.
method Introduction to relevant deep learning models, analysis of SAR data characteristics, review of state-of-the-art applications, and future research directions.
result Unlocking the potential of deep learning in SAR data processing.
This work reveals a new scaling law for optimal design of multirotor aerial vehicles.
problem Designing optimal configurations for fully-actuated multirotor aerial vehicles.
method Formulated on the product manifold of Projective Lines \RP^2^N, minimizing a coordinate-invariant Log-Volume isotropy metric.
result The topology of the global optima is governed by the symmetry of the chassis, leading to a N-5 Scaling Law.
GNMR controls runtime stability in low-precision language model training.
problem Efficient low-precision training faces numerical risks at specific operators.
method GNMR compares gradient norms to historical means, applying bounded recovery actions.
result GNMR preserves high-fidelity quality with sparse, budgeted recovery.
The introduction of automated flight control and management systems have made possible aircraft designs that sacrifice arodynamic stability in order to incorporate stealth technology intro their shape, operate more efficiently, and are highly maneuverable. Therefore, modern flight management systems are reliant on mult…
Probabilistic programming aids in automatically dating ice cores, reducing manual error and uncertainty.
problem Automatically dating ice cores with high accuracy and capturing uncertainty.
method Probabilistic models and probabilistic programming for automatic inference.
result Demonstrated the use of probabilistic programming for ice core dating, showcasing its benefits and limitations.
A new model for simulating cloth manipulation in robots, accurate to within 1cm.
problem Accurately simulating cloth manipulation in robots, especially in moderate stress environments.
method A continuous, isometric strain model for textiles, treating them as inextensible surfaces with only isometric motions. Aerodynamic effects are incorporated through virtual uncoupling of mass.
result Simulations are accurate to within 1cm compared to real-world manipulation, even with coarse meshes.
One-Dimensional Pricing of CPPIq-fin.PR
Constant Proportion Portfolio Insurance (CPPI) is an investment strategy designed to give participation in the performance of a risky asset while protecting the invested capital. This protection is however not perfect and the gap risk must be quantified. CPPI strategies are path-dependent and may have American exercise…
EagerPy simplifies writing code for multiple deep learning frameworks.
problem Code duplication and framework lock-in when using different deep learning libraries.
method Integrates multiple frameworks into a single Python framework.
result Automatic compatibility across PyTorch, TensorFlow, JAX, and NumPy.
Study links public concern in Italy to financial markets worldwide.
problem Understanding public concern's impact on financial markets during pandemics.
method Used Google Trends data from YouTube, News, and Search to measure public concern and correlate it with stock index returns.
result Public concern in Italy drives concerns in other countries and explains stock index returns of multiple nations.
Stochastic variational inference (SVI) employs stochastic optimization to scale up Bayesian computation to massive data. Since SVI is at its core a stochastic gradient-based algorithm, horizontal parallelism can be harnessed to allow larger scale inference. We propose a lock-free parallel implementation for SVI which a…
Stochastic Maps, Wealth Distribution in Random Asset Exchange Models and the Marginal Utility of Relative Wealthcond-mat.stat-mech
We look at how asset exchange models can be mapped to random iterated function systems (IFS) giving new insights into the dynamics of wealth accumulation in such models. In particular, we focus on the "yard-sale" (winner gets a random fraction of the poorer players wealth) and the "theft-and-fraud" (winner gets a rando…
Stochastic variational inference (SVI), the state-of-the-art algorithm for scaling variational inference to large-datasets, is inherently serial. Moreover, it requires the parameters to fit in the memory of a single processor; this is problematic when the number of parameters is in billions. In this paper, we propose e…