New method improves inference for discrete diffusion models, achieving better quality and efficiency.
problem High dimensionality of discrete diffusion models causes inference challenges.
method Developed high-order numerical inference schemes for discrete diffusion models.
result Second-order accuracy of the θ-Trapezoidal method in KL divergence. This work analyzes discrete diffusion models using stochastic integrals, providing error bounds and insights.
problem Error analysis for discrete diffusion models remains less understood.
method Proposes a comprehensive framework based on Lévy-type stochastic integrals.
result Obtains the first error bound for the τ-leaping scheme in KL divergence. SGD learns neural networks with a complexity measure called leap.
problem Time complexity of SGD learning on neural networks.
method Introduced a complexity measure called leap, proved conjecture for Gaussian data, and showed saddle-to-saddle dynamics.
result Proved a conjecture about the time complexity of learning functions with low-dimensional support.
LEAPS samples discrete distributions via CTMCs and locally equivariant networks.
problem Sampling from discrete distributions with known normalization.
method Continuous-time Markov chain, locally equivariant functions, attention layers, convolutional networks.
result LEAPS minimizes the variance of importance weights, improving sampling efficiency.
Graph edges, along with their labels, can represent information of fundamental importance, such as links between web pages, friendship between users, the rating given by users to other users or items, and much more. We introduce LEAP, a trainable, general framework for predicting the presence and properties of edges on…
Two-layer networks learn faster with batch reuse, overcoming information and leap exponents.
problem Limitations of gradient flow and single-pass GD in learning multi-index target functions.
method Multi-pass gradient descent that reuses batches, analyzed using Dynamical Mean-Field Theory.
result Two-time-step overlap with target subspace for non-staircase functions, overcoming information and leap exponents.
The paper analyzes sampling efficiency of discrete diffusion models, providing sharp and adaptive guarantees.
problem Theoretical foundations of discrete diffusion models, especially sampling efficiency.
method Continuous-time Markov chain (CTMC) formulation, τ-leaping-based samplers, effective total correlation. result The τ-leaping algorithm achieves an iteration complexity of order ildeO(d/ε) for uniform discrete diffusion, improving existing bounds by a factor of d. We propose a novel neural network embedding approach to model power transmission grids, in which high voltage lines are disconnected and reconnected with one-another from time to time, either accidentally or willfully. We call our architeture LEAP net, for Latent Encoding of Atypical Perturbation. Our method implements…
In this article, a compact finite difference method is proposed for pricing European and American options under jump-diffusion models. Partial integro-differential equation and linear complementary problem governing European and American options respectively are discretized using Crank-Nicolson Leap-Frog scheme. In pro…
Study efficient estimation of hidden subspaces in Gaussian Multi-index models.
problem Estimating hidden subspaces in Gaussian Multi-index models with low-dimensional projections.
method Introduced the generative leap exponent and developed an agnostic sequential estimation procedure using spectral U-statistics.
result Achieved optimal sample complexity of $n=Θ(d^{1 \vee \k/2})$ for efficient estimation.
Corrected samplers reduce discretization error in discrete flow models without additional computational cost.
problem Discretization error in samplers for discrete flow models.
method Established non-asymptotic error bounds for samplers, proposed time-corrected and location-corrected samplers.
result Location-corrected sampler has lower complexity and better generation quality.
In complex transfer learning scenarios new tasks might not be tightly linked to previous tasks. Approaches that transfer information contained only in the final parameters of a source model will therefore struggle. Instead, transfer learning at a higher level of abstraction is needed. We propose Leap, a framework that …
Building deep reinforcement learning agents that can generalize and adapt to unseen environments remains a fundamental challenge for AI. This paper describes progresses on this challenge in the context of man-made environments, which are visually diverse but contain intrinsic semantic regularities. We propose a hybrid …
LEAP identifies latent causal variables from temporal data.
problem Recovering time-delayed latent causal variables from general temporal data.
method Proposes LEAP, a framework that extends VAEs with constraints for temporally causal latent processes.
result Successfully identifies temporally causal latent processes from observed variables under various dependency structures.
Feature selection and attribute reduction are crucial problems, and widely used techniques in the field of machine learning, data mining and pattern recognition to overcome the well-known phenomenon of the Curse of Dimensionality, by either selecting a subset of features or removing unrelated ones. This paper presents …
In this report, an automated bartender system was developed for making orders in a bar using hand gestures. The gesture recognition of the system was developed using Machine Learning techniques, where the model was trained to classify gestures using collected data. The final model used in the system reached an average …
A new method identifies a stable subnetwork in overparameterized student models.
problem Identifying a stable subnetwork in overparameterized student models.
method Spectral representation of linear transfer of information, focusing on eigenvalues and eigenvectors.
result A stable student substructure is isolated that mirrors the true complexity of the teacher.
We consider the problem of impulse response estimation of stable linear single-input single-output systems. It is a well-studied problem where flexible non-parametric models recently offered a leap in performance compared to the classical finite-dimensional model structures. Inspired by this development and the success…
Survey on discovering causal relationships from data.
problem Discover causal relationships from data.
method Modern, continuous optimization methods for structure learning.
result Survey of methods and resources for structure discovery.
Designing of touchless user interface is gaining popularity in various contexts. Using such interfaces, users can interact with electronic devices even when the hands are dirty or non-conductive. Also, user with partial physical disability can interact with electronic devices using such systems. Research in this direct…
Medical applications challenge today's text categorization techniques by demanding both high accuracy and ease-of-interpretation. Although deep learning has provided a leap ahead in accuracy, this leap comes at the sacrifice of interpretability. To address this accuracy-interpretability challenge, we here introduce, fo…
Reweighted ALPS improves sampling from multimodal distributions using warm start points.
problem Sampling from multimodal distributions is hard due to exponential mixing times.
method Introduces Reweighted ALPS, a modified Annealed Leap-Point Sampler that uses warm start points.
result First polynomial-time bound for Re-ALPS in a general setting, under a natural assumption.
Kernel methods can learn hierarchical polynomials efficiently.
problem Learning hierarchical structure from data.
method Iteratively reweighting kernel machines using derivatives.
result Efficient learning of hierarchical polynomials.
Study shows how price protection affects online learning algorithms for dynamic pricing.
problem Impact of price protection guarantee on online learning algorithms for dynamic pricing.
method Characterized the effect of price protection period length on optimal regret, proposed LEAP algorithm.
result Optimal regret is Θ(√T + min{M, T^2/3}) with LEAP matching lower bounds up to logarithmic factors.
One of the defining characteristics of human creativity is the ability to make conceptual leaps, creating something surprising from typical knowledge. In comparison, deep neural networks often struggle to handle cases outside of their training data, which is especially problematic for problems with limited training dat…
Survey on quantum computing and neural networks.
problem Understanding and comparing quantum computing and neural networks.
method Introduction to quantum computing concepts, explanation of quantum computing paradigms, and analysis of quantum neural networks.
result Current state-of-the-art in quantum neural networks.
Normalizing flows are shown to be equivalent to Bayesian networks, revealing new insights.
problem Understanding the limitations and capabilities of normalizing flows.
method Revisiting normalizing flows as probabilistic graphical models and analyzing their structure.
result Normalizing flows can be reduced to Bayesian networks, revealing new insights into their structure and capabilities.
MEC-IP uses IP to efficiently find MECs in BNs from observational data.
problem Discovering Markov Equivalent Classes (MECs) in Bayesian Networks (BNs) efficiently.
method Clique-focusing strategy and EMSG for MEC discovery via Integer Programming.
result Significant reduction in computational time and improved accuracy.
FutureQuant Transformer predicts price ranges and volatility for futures trading.
problem Complex futures trading with real-time LOBs and vast data.
method FutureQuant Transformer model using attention mechanisms.
result Significantly improved trading performance with an average gain of 0.1193%.
New method uses birth-death process and exploration component to accelerate sampling from multimodal distributions.
problem Sampling from multimodal probability distributions efficiently.
method Combines birth-death process and exploration component to accelerate sampling.
result Proves exponential asymptotic convergence under mild assumptions.
The study explores how machine learning can enhance scientific research.
problem Improving scientific models with machine learning.
method Analysis of data-driven models versus manually added variables in regression.
result Complex models may not always improve over simpler ones in scientific contexts.
In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring. As a result, an increasing number of AI-enabled applications are being developed targeting ubiquitous and mobile devices. While deep ne…
Review of mean-field methods for neural network inference.
problem Understanding neural network learning from a theoretical perspective.
method Mean-field methods, high-temperature expansions, replica method, message passing algorithms.
result Equivalences and complementarities of mean-field methods.
Randomly biased data makes complex models as easy to learn as simple ones.
problem Learning complex models like multi-index and sparse Boolean functions.
method Introducing a small random shift in the first moment of the data distribution.
result Randomly biased data makes Gaussian single index models and sparse Boolean functions as easy to learn as linear functions.
TLRS improves predictive power of mined formulaic alpha factors.
problem Sparse rewards in RL for mining formulaic alpha factors.
method Trajectory-level Reward Shaping (TLRS) with reward centering.
result TLRS boosts predictive power by 9.29% over existing methods.
Neural LNS improves vehicle routing performance.
problem Optimizing vehicle routes with constraints.
method Integrates deep learning with large neighborhood search.
result Significantly outperforms existing methods on CVRP.
We propose a fast second-order method that can be used as a drop-in replacement for current deep learning solvers. Compared to stochastic gradient descent (SGD), it only requires two additional forward-mode automatic differentiation operations per iteration, which has a computational cost comparable to two standard for…
VTrackIt creates a synthetic dataset with infrastructure and vehicle info for AVs.
problem Lack of infrastructure and pooled vehicle info in existing AV datasets.
method Developed VTrackIt, a synthetic dataset with intelligent infrastructure and pooled vehicle info, and introduced InfraGAN for trajectory predictions.
result VTrackIt reduces high-risk edge cases in AV trajectory predictions.
MarketSenseAI uses AI to select stocks with 10-30% excess alpha.
problem Selecting profitable stocks in financial markets.
method Integrates GPT-4 for analyzing diverse data and decision-making.
result Demonstrated exceptional performance with up to 72% cumulative return.
New method tackles rugged optimization landscapes in contact-rich scenarios.
problem Optimization challenges in dynamic environments with deformable objects.
method Combines Bayesian optimization with semi-local 'leaps' for global search.
result Outperforms gradient-based and gradient-free baselines in simulation and real robot experiments.
The introduction of deep learning and transfer learning techniques in fields such as computer vision allowed a leap forward in the accuracy of image classification tasks. Currently there is only limited use of such techniques in neuroscience. The challenge of using deep learning methods to successfully train models in …
In recent years, the use of bio-sensing signals such as electroencephalogram (EEG), electrocardiogram (ECG), etc. have garnered interest towards applications in affective computing. The parallel trend of deep-learning has led to a huge leap in performance towards solving various vision-based research problems such as o…
Paper tackles variable-length, incomplete wearable sensor data to improve personalized insights.
problem Variable-length and incomplete time series data from wearable sensors.
method HeartSpace integrates a time series encoding module and pattern aggregation network, along with a Siamese-triplet network for representation learning.
result Empirical evaluation shows significant performance gains in personality prediction, demographics inference, and user identification.
New probabilistic scheme combines deep learning with Runge-Kutta methods for solving PDEs.
problem Solving high-dimensional semi-linear parabolic PDEs efficiently.
method Probabilistic scheme using deep learning and Runge-Kutta methods.
result Crank-Nicolson schemes are efficient in terms of precision, computational cost, and numerical implementation.
FMT model improves multimodal sequential learning across language, vision, and acoustic data.
problem Modeling spatio-temporal dynamics across multiple modalities.
method Factorized Multimodal Transformer (FMT) that models intramodal and intermodal dynamics in a factorized manner.
result FMT outperforms existing models on 3 datasets and 21 labels, setting new state of the art.
It was proved in 1998 by Ben-David and Litman that a concept space has a sample compression scheme of size d if and only if every finite subspace has a sample compression scheme of size d. In the compactness theorem, measurability of the hypotheses of the created sample compression scheme is not guaranteed; at the same…
Study SL(2,C) character schemes for finitely generated groups.
problem Characterize SL(2,C) representations of finitely generated groups.
method Define coordinate rings and equations for SL(2,C) character schemes.
result Explicit equations for character schemes of finitely presented groups.
A new method for computing image curvature efficiently and accurately.
problem Low performance, low accuracy, and requirement of second order differentiability in conventional computation schemes.
method Proposes a novel discrete computation scheme for weighted Gaussian curvature.
result More accurate, computationally more efficient, and does not require second order differentiability.