Optimizes wide low-rank neural networks for reduced parameters and cost.
problem Reducing the number of learnable parameters in wide neural networks.
method Analyzed edge-of-chaos dynamics and derived formulae for optimal weight and bias variances.
result Optimal weight and bias variances for low-rank networks follow from multiplicative scaling.
Optimal privacy-preserving ranking from noisy comparisons.
problem Protecting individual privacy in ranking from noisy comparisons.
method Differentially private ranking algorithms under edge and individual differential privacy.
result Achieved minimax optimal rates of convergence under privacy constraints.
We characterize distributional equivalence in latent-variable models with cycles.
problem Lack of an equivalence characterization for latent-variable causal models with cycles.
method Established graphical criterion for distributional equivalence and developed edge rank constraints.
result First equivalence characterization without structural assumptions for latent-variable models with cycles.
OL4EL optimizes edge learning on resource-constrained servers.
problem Resource constraints on edge servers hinder effective distributed machine learning.
method Online Learning for EL (OL4EL) framework using budget-limited multi-armed bandit model.
result OL4EL significantly improves learning performance while conserving resources.
We propose a new method for embedding graphs while preserving directed edge information. Learning such continuous-space vector representations (or embeddings) of nodes in a graph is an important first step for using network information (from social networks, user-item graphs, knowledge bases, etc.) in many machine lear…
Low-rank training improves neural network training on edge devices with non-volatile memory.
problem Training neural networks on edge devices with non-volatile memory, especially in terms of write density and auxiliary memory.
method Low-rank training scheme to address write density and auxiliary memory limitations.
result The low-rank training technique outperforms standard SGD in accuracy and weight writes.
A new method for identifying causal directions in complex systems.
problem Identifying causal relationships in nonlinear systems with limited data.
method Sequential edge orientation approach using pairwise additive noise model.
result The method can recover true causal DAGs under nonlinear additive noise models.
Proposes a model for identifying edges in low-rank dynamical networks.
problem Inability of conventional methods to handle low-rank dynamical networks.
method Low rank dynamical network model with causal Wiener filtering.
result Consistent method for estimating all network edges.
In the emerging advancement in the branch of autonomous robotics, the ability of a robot to efficiently localize and construct maps of its surrounding is crucial. This paper deals with utilizing thermal-infrared cameras, as opposed to conventional cameras as the primary sensor to capture images of the robot's surroundi…
Edge language models show bias over time, especially on resource-constrained devices.
problem Bias in edge language models on resource-constrained devices.
method Comparative analysis of text-based bias across edge, cloud, and desktop environments; optimized Llama-2 model on Raspberry Pi 4; feedback loop mechanism to correct bias.
result Llama-2 on Raspberry Pi 4 shows 43.23% and 21.89% more bias over time compared to cloud and desktop models.
TOCO framework compresses neural networks based on tolerance analysis.
problem Deploying large neural networks on edge devices with limited resources.
method TOCO uses tolerance analysis to perform fine-grained compression, allowing flexibility to hardware changes.
result Fine-grained compression of neural networks on edge devices.
The stringent requirements for low-latency and privacy of the emerging high-stake applications with intelligent devices such as drones and smart vehicles make the cloud computing inapplicable in these scenarios. Instead, edge machine learning becomes increasingly attractive for performing training and inference directl…
Bayesian method infers transition matrices from incomplete graph data with topological constraints.
problem Inference of transition matrices from incomplete graph data with topological constraints.
method Bayesian approach using repeated interactions and a topological prior.
result Higher accuracy in inferring transition probabilities, improving downstream tasks.
We present a graph-based semi-supervised learning (SSL) method for learning edge flows defined on a graph. Specifically, given flow measurements on a subset of edges, we want to predict the flows on the remaining edges. To this end, we develop a computational framework that imposes certain constraints on the overall fl…
Paper proposes SaiyanH to learn BNs with full evidence propagation from dependent variables.
problem Learning disjoint subgraphs that prevent full evidence propagation.
method SaiyanH, a hybrid structure learning algorithm.
result SaiyanH outperforms state-of-the-art algorithms in reconstructing true DAGs.
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there is a need for compression techniques that can achieve significant compression wit…
We propose a number of techniques for obtaining a global ranking from data that may be incomplete and imbalanced -- characteristics almost universal to modern datasets coming from e-commerce and internet applications. We are primarily interested in score or rating-based cardinal data. From raw ranking data, we construc…
Improved machine learning with reduced tensor rank constraints and dropout.
problem Efficiently approximating large tensors in machine learning.
method Tree tensor networks with CP rank constraints and tensor dropout.
result Low-rank TTN classifier achieves 90.3% accuracy in Fashion-MNIST.
We analyze the structure of covariance matrices under graph constraints.
problem Analyzing the structure of covariance matrices under graph constraints.
method We explore the algebraic structure of the solution space of convex optimization problem Constrained Minimum Trace Factor Analysis (CMTFA) under a latent star topology.
result CMTFA can have either a rank 1 or a rank n-1 solution, with conditions for both.
The problem of low-rank approximation with convex constraints, which appears in data analysis, system identification, model order reduction, low-order controller design and low-complexity modelling is considered. Given a matrix, the objective is to find a low-rank approximation that meets rank and convex constraints, w…
Networks are a useful representation for data on connections between units of interests, but the observed connections are often noisy and/or include missing values. One common approach to network analysis is to treat the network as a realization from a random graph model, and estimate the underlying edge probability ma…
POET enables large neural network training on tiny devices with reduced energy.
problem Training large neural networks on memory-limited edge devices.
method Jointly optimizes rematerialization and paging for memory reduction, formulating an MILP for energy-efficient training.
result POET trains ResNet-18 and BERT within Cortex-M memory constraints, outperforming current methods in energy efficiency.
New algorithm tackles low-rank constraints in optimal transport problems.
problem Optimal transport problems with low-rank constraints.
method Explicit factorization of low-rank couplings as a product of sub-coupling factors linked by a common marginal.
result Stationary convergence of the algorithm proved.
Most learning methods with rank or sparsity constraints use convex relaxations, which lead to optimization with the nuclear norm or the ℓ1-norm. However, several important learning applications cannot benefit from this approach as they feature these convex norms as constraints in addition to the non-convex rank a…
We consider the problem of noisy 1-bit matrix completion under an exact rank constraint on the true underlying matrix M∗. Instead of observing a subset of the noisy continuous-valued entries of a matrix M∗, we observe a subset of noisy 1-bit (or binary) measurements generated according to a probabilistic model. W…
This paper proposes a mechanism to produce equivalent Lipschitz surrogates for zero-norm and rank optimization problems by means of the global exact penalty for their equivalent mathematical programs with an equilibrium constraint (MPECs). Specifically, we reformulate these combinatorial problems as equivalent MPECs by…
Minimizing the rank of a matrix subject to constraints is a challenging problem that arises in many applications in control theory, machine learning, and discrete geometry. This class of optimization problems, known as rank minimization, is NP-HARD, and for most practical problems there are no efficient algorithms that…
We show that if X is a minimal length carrier graph in a hyperbolic 3-manifold, M, then if X contains a sufficiently short edge, it must contain a short circuit, as well. The meaning of "short" depends only on the rank of the fundamental group of M. We also expand the class of manifolds which are known to have minimal …
Paper improves MVSC using tensor low-rank modeling.
problem Improving multi-view spectral clustering.
method Structured tensor low-rank norm for MVSC optimization.
result Proposed method outperforms state-of-the-art methods.
Extends RRR to capture nonlinear interactions in multi-response regression.
problem Complex relationships in real-world data cannot be adequately modeled by linear interactions.
method Introduces Higher Order Reduced Rank Regression (HORRR) using tensor representations and Tucker decomposition.
result HORRR can capture nonlinear interactions in multi-response regression.
This work extends the randomized shortest paths (RSP) model by investigating the net flow RSP and adding capacity constraints on edge flows. The standard RSP is a model of movement, or spread, through a network interpolating between a random-walk and a shortest-path behavior [30, 42, 49]. The framework assumes a unit f…
Algorithm samples fair rankings to ensure individual fairness while maintaining group fairness.
problem Fair ranking tasks with group fairness constraints and uncertainty in item utilities.
method Efficient algorithm that samples rankings from an individually-fair distribution ensuring group fairness.
result Expected utility of output ranking is at least α times optimal fair solution, where α depends on utilities and constraints.
New algorithm improves deep learning models' robustness without sacrificing accuracy.
problem Low-rank methods compromise model robustness against adversarial perturbations.
method Robust low-rank training via approximate orthonormal constraints.
result Ensures well-conditioning and better adversarial robustness without sacrificing model accuracy.
EDG generates Boltzmann samples from latent variables efficiently.
problem Sampling from complex energy functions in high dimensions.
method Combines variational autoencoders and diffusion models; uses a decoder and diffusion-based encoder.
result EDG outperforms existing methods in various sampling tasks.
Sparse connectivity improves generalization in neural networks below the Edge of Stability.
problem Generalization guarantees for fully-connected networks fail at the Edge of Stability.
method Analyzed sparse connectivity's impact on generalization in two-layer ReLU networks.
result Sparse connectivity changes the effective constraint, leading to non-vacuous generalization bounds.
Spectral ranking methods are improved against semi-random graph sampling.
problem Improving spectral ranking methods in semi-random graph sampling.
method Investigating entry-wise error of spectral algorithms against a semi-random adversary.
result Asymptotic performance can be recovered by reweighting observed edges.
Graph neural networks improve with edge similarity constraints in RNA structure analysis.
problem Lack of edge similarity constraints in graph neural networks.
method Introduced a graph neural network layer that leverages prior information about edge similarities.
result Edge similarity constraints do not enhance performance in graph neural networks.
Fairness constraints improve exact recovery in structured prediction models.
problem Exact recovery of fair binary node labels from noisy observations.
method Analyzed Globerson et al. (2015) model with fairness constraints and improved exact recovery for graphs with poor expansion properties.
result Fairness constraints improve the probability of exact recovery from noisy observations.
Paper develops compact formulations for optimization problems with rank-one convex functions and indicator variables.
problem Optimization problems involving rank-one convex functions with support constraints.
method Perspective reformulation techniques to exploit conic structure and establish convex hull results.
result Systematic perspective formulations for convex hull descriptions of sets with nonlinear separable or non-separable objective functions and combinatorial constraints.
We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint. For this, we show conditions under which the proximal operator of a function involving the rank constraint is locally identical to the proximal operator of its convex envelope, hen…
We study the supersymmetric Wilson loop as introduced by Caron-Huot, which attaches to lightlike polygons certain edge and vertex operators, whose shape is determined by supersymmetry constraints. We state explicit formulas for the vertex operators to all orders in the Graßmann expansion, thus filling a gap in the lite…
Method generates resource-optimized ML models for different platforms.
problem Deployment of deep learning models on edge platforms requires model reduction and retraining.
method Conditional Neural Architecture Search using Generative Adversarial Networks (GAN)
result Successfully generates resource-optimized ML models for different platforms.
Introduces nondecreasing rank for matrices and tensors, developing methods and applications.
problem Finding low-rank approximations for matrices and tensors with monotonic constraints.
method Developed a variant of hierarchical alternating least squares algorithm for finding low ND rank approximations.
result Low ND rank factorizations can be found and interpreted for real-world datasets.
The paper tackles fair correlation clustering with fairness constraints.
problem Minimizing disagreements while adhering to fairness constraints for clustering.
method Two variants of fairness constraints are considered: equal distribution and relative bounds. Approximation algorithms are developed for these constraints.
result Approximation algorithms for fair correlation clustering with theoretical guarantees and empirical validation.
Develops new oracle inequalities for Gaussian ranking estimators.
problem Lack of rigorous theoretical support for Gaussian ranking estimators.
method Novel oracle inequalities for regularized pairwise ranking.
result Derives fast learning rates under general dimension assumptions.
Paper proposes a new algorithm for graph learning with covariance constraints.
problem Graphical models and factor analysis not jointly leveraged in graph learning processes.
method Penalized maximum likelihood estimation of an elliptical distribution with Riemannian optimization.
result Effectiveness of the proposed approach demonstrated on real-world data sets.
Differentially private graph learning via bounded sensitivity PPR.
problem Protecting user data in graph learning algorithms.
method Proposes a sensitivity-bounded personalized PageRank (PPR) algorithm.
result Achieves similar accuracy to non-private algorithms with large degrees.
Latent Euclidean embedding models a given network by representing each node in a Euclidean space, where the probability of two nodes sharing an edge is a function of the distances between the nodes. This implies that for two nodes to share an edge with high probability, they must be relatively close in all dimensions. …