arXiv research

This work proposes an online learning approach to tighten constraints in stochastic control problems.

Unified framework for hard affine SDP constraints in vRKHSs.

Safety filter for unknown discrete-time systems with learned models and noise covariance.

We describe a new technique for computing lower-bounds on the minimum energy configuration of a planar Markov Random Field (MRF). Our method successively adds large numbers of constraints and enforces consistency over binary projections of the original problem state space. These constraints are represented in terms of …

Optimizes decisions in time-varying distributions using online stochastic methods and Wasserstein distance.

SafeQ-Learning uses Wasserstein DRO to ensure safety in online learning.

FROWN optimizes neural network robustness, improving safety in deep learning.

Dual decomposition provides a tractable framework for designing algorithms for finding the most probable (MAP) configuration in graphical models. However, for many real-world inference problems, the typical decomposition has a large integrality gap, due to frustrated cycles. One way to tighten the relaxation is to intr…

Optimizes bank capital structure under Basel III constraints, simplifying complex dynamics.

Paper resolves open problems on sample complexity in binary hypothesis testing.

Safe learning in uncertain systems with state measurements and optimization.

Paper tackles hard shape constraints in kernel machines.

In this paper we present a new approach for tightening upper bounds on the partition function. Our upper bounds are based on fractional covering bounds on the entropy function, and result in a concave program to compute these bounds and a convex program to tighten them. To solve these programs effectively for general r…

We study the problem of instance segmentation in biological images with crowded and compact cells. We formulate this task as an integer program where variables correspond to cells and constraints enforce that cells do not overlap. To solve this integer program, we propose a column generation formulation where the prici…

We propose a novel training algorithm for reinforcement learning which combines the strength of deep Q-learning with a constrained optimization approach to tighten optimality and encourage faster reward propagation. Our novel technique makes deep reinforcement learning more practical by drastically reducing the trainin…

Paper proposes efficient network pruning method for deep neural networks.

Paper tightens optimization bounds using conformal prediction.

The paper improves nonparametric confidence bands for band-limited functions.

Algorithm ensures safe optimization under unknown constraints.

Improved neural network robustness certification through tighter convex relaxations.

Optimal insurance contract limits insurer's risk exposure variance.

We analyze variational inference for highly symmetric graphical models such as those arising from first-order probabilistic models. We first show that for these graphical models, the tree-reweighted variational objective lends itself to a compact lifted formulation which can be solved much more efficiently than the sta…

Study optimizes pricing under uncertainty and capacity constraints.

The paper tackles Neyman-Pearson classification control issues.

New bounds tighten the generalization error of Gibbs algorithm.

Sparse principal component analysis (PCA) involves nonconvex optimization for which the global solution is hard to obtain. To address this issue, one popular approach is convex relaxation. However, such an approach may produce suboptimal estimators due to the relaxation effect. To optimally estimate sparse principal su…

Optimal experiments tighten causal effect bounds efficiently.

Many computer vision and medical imaging problems are faced with learning from large-scale datasets, with millions of observations and features. In this paper we propose a novel efficient learning scheme that tightens a sparsity constraint by gradually removing variables based on a criterion and a schedule. The attract…

Paper develops online learning-based risk-averse MPC for uncertain systems.

New framework tightens certified robustness gaps in machine learning models.

Polynomial bound on tightening curves on surfaces without increasing crossings.

Tail-Safe hedging uses reinforcement learning with a safety layer to manage financial risks.

Bounding the generalization error of learning algorithms has a long history, which yet falls short in explaining various generalization successes including those of deep learning. Two important difficulties are (i) exploiting the dependencies between the hypotheses, (ii) exploiting the dependence between the algorithm'…

In this note we establish estimates for the harmonic map heat flow from $S^1$ into a closed manifold, and use it to construct sweepouts with the following good property: each curve in the tightened sweepout, whose energy is close to the maximal energy of curves in the sweepout, is itself close to a closed geodesic.

ML Compass helps organizations choose AI models that balance utility, cost, and compliance.

Paper tightens statistical aggregation results using local complexity.

Variational inference has become one of the most widely used methods in latent variable modeling. In its basic form, variational inference employs a fully factorized variational distribution and minimizes its KL divergence to the posterior. As the minimization can only be carried out approximately, this approximation i…

We present a simple agent-based model of a financial system composed of leveraged investors such as banks that invest in stocks and manage their risk using a Value-at-Risk constraint, based on historical observations of asset prices. The Value-at-Risk constraint implies that when perceived risk is low, leverage is high…

Improved bounds on geodesic lengths in Riemannian surfaces.

Framework identifies population quantities from MNAR feedback using weak shadow variables from pretrained models.

Factorization machine (FM) is a popular machine learning model to capture the second order feature interactions. The optimal learning guarantee of FM and its generalized version is not yet developed. For a rank $k$ generalized FM of $d$ dimensional input, the previous best known sampling complexity is $\mathcal{O}[k^{3…

In this paper we propose a problem-driven scenario generation approach to the single-period portfolio selection problem which use tail risk measures such as conditional value-at-risk. Tail risk measures are useful for quantifying potential losses in worst cases. However, for scenario-based problems these are problemati…

We show that the variational representations for f-divergences currently used in the literature can be tightened. This has implications to a number of methods recently proposed based on this representation. As an example application we use our tighter representation to derive a general f-divergence estimator based on t…

New method tightens bounds on causation probabilities using independent datasets.

Generalizes neural network verification by adding arbitrary cutting planes.

We present new computations of approximately length-minimizing polygons with fixed thickness. These curves model the centerlines of "tight" knotted tubes with minimal length and fixed circular cross-section. Our curves approximately minimize the ropelength (or quotient of length and thickness) for polygons in their kno…

Paper proposes a 1-bit mean estimation method with near-optimal sample complexity.

UCRL3 improves UCRL2's efficiency in reinforcement learning by reducing exploration.