Research
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

132265397529 · Jun 202019922001200920172026
48 results for smooth convex loss

We establish linear regret bounds for convex smooth losses using Fenchel-Young losses.

problem Establishing linear regret bounds for convex smooth losses.
method Constructing a convex smooth surrogate loss using Fenchel-Young losses generated by the convolutional negentropy.
result We derive a smooth loss with a linear surrogate regret bound.

Paper relaxes SGD privacy and generalization guarantees for non-smooth convex losses.

problem Privacy and generalization in SGD for non-smooth convex losses.
method Relaxes Lipschitz and strong smoothness assumptions to Hölder smoothness, proving (ε,δ)(ε,δ)-DP and optimal excess risk.
result Noisy SGD with αα-Hölder smooth losses achieves optimal excess risk with linear gradient complexity for α1/2α \geq 1/2.

In statistical learning theory, convex surrogates of the 0-1 loss are highly preferred because of the computational and theoretical virtues that convexity brings in. This is of more importance if we consider smooth surrogates as witnessed by the fact that the smoothness is further beneficial both computationally- by at…

2014-02-07abs ↗pdf ↗

Paper introduces a new GG^\star regret measure for online convex optimization with smooth losses.

problem Online convex optimization with smooth losses.
method Introduces a new GG^\star regret measure that depends on the cumulative squared gradient norm.
result The GG^\star regret can be arbitrarily sharper than existing measures when losses have vanishing curvature.

Improved online learning for hidden-convex losses achieves optimal regret.

problem Adversarial online learning with nonconvex losses that become convex after reparameterization.
method Algorithmic equivalence between OGD and OMD on convex losses, with Hessian compatibility condition.
result OGD achieves O(T)\mathcal{O}(\sqrt{T}) regret for hidden-convex losses, matching optimal rate.

New algorithms for differentially private optimization in convex and non-convex settings with near-optimal rates.

problem Differentially private optimization in convex and non-convex settings.
method Developed algorithms for convex and non-convex settings with near-optimal excess population risk.
result Achieved near-optimal rates in near-linear time for convex settings and nearly dimension independent rates for non-convex settings.

Paper improves privacy and utility of SGD with bounded domain and smooth losses.

problem Lack of tight privacy bounds and practical assumptions in DPSGD.
method Rigorous privacy characterization for DPSGD with general L-smooth and non-convex loss functions, tracking privacy loss over iterations.
result Privacy loss converges without convexity assumption for bounded domain, improving utility.

Full-batch GD achieves generalization close to any stationary point with fewer assumptions.

problem Generalization and excess risk bounds for smooth losses, including non-Lipschitz and nonconvex cases.
method Path-dependent analysis of GD's generalization error, focusing on optimization error and stability.
result Generalization error is tightly bound in terms of optimization error and iteration count, bypassing common assumptions.

Paper improves stability analysis of SGD for various loss functions and data distributions.

problem Improving stability analysis of SGD for non-convex loss functions and data distributions.
method Analyzes stability of SGD for convex and non-convex loss functions, and improves data-dependent bounds.
result Improved stability bounds for non-convex loss functions and convex regularized loss functions.

Unified analysis of stochastic gradient methods for convex and smooth optimization.

problem Minimizing composite convex and smooth functions.
method Unified convergence analysis of various stochastic gradient methods.
result Unified convergence rates for a variety of methods including proximal SGD, variance reduced methods, quantization, and coordinate descent.

The Nyström method improves learning efficiency for convex losses.

problem Improving computational efficiency in empirical risk minimization.
method Using random subspaces to approximate hypothesis spaces in convex loss functions.
result Computational gains can be achieved without sacrificing learning performance for general convex Lipschitz losses.

New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.

problem Online convex optimization in non-stationary environments.
method Proposed novel online algorithms exploiting smoothness to reduce dynamic regret.
result Dynamic regret improved to O(T)\mathcal{O}(T) for convex and smooth functions.

Algorithm minimizes loss and constraint violations in online convex optimization with smooth penalties.

problem Minimizing loss and constraint violations in online convex optimization with smooth penalties.
method Projected gradient descent over a set around the current action.
result Both dynamic regret and constraint violation are bounded by the path-length.

New algorithm for robust high-dimensional linear regression is both fast and statistically optimal.

problem Challenges in high-dimensional linear regression under heavy-tailed noise or outliers.
method Projected sub-gradient descent algorithm for sparse and low-rank regression problems.
result Algorithm achieves linear convergence and statistical optimality under various noise conditions.

New research shows many batch selection methods for training work just as well as full batch training.

problem Finding optimal batch selection methods for training.
method Analysis of mini-batch Gradient Descent (GD) and Stochastic GD (SGD) with various batch selection rules.
result All mini-batch schedules, including deterministic ones, generalize optimally for smooth Lipschitz-convex/nonconvex/strongly-convex loss functions.

New method turns optimization algorithms into uniformly stable learning algorithms for non-Euclidean norms.

problem Non-Euclidean norms in binary classification problems.
method Black-box reduction method using uniformly convex regularizers.
result Achieves optimal statistical risk bounds on excess risk for non-Euclidean norms.

Improved online convex optimization bounds between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds improve on previous results by reducing dependence on maximum gradient length to variance of gradients.

We propose in this paper a general framework for deriving loss functions for structured prediction. In our framework, the user chooses a convex set including the output space and provides an oracle for projecting onto that set. Given that oracle, our framework automatically generates a corresponding convex and smooth l…

2019-10-24abs ↗pdf ↗

We investigate online convex optimization in changing environments, and choose the adaptive regret as the performance measure. The goal is to achieve a small regret over every interval so that the comparator is allowed to change over time. Different from previous works that only utilize the convexity condition, this pa…

2019-04-26abs ↗pdf ↗

New DP algorithm improves privacy and efficiency for convex optimization.

problem Efficient, DP algorithms for convex optimization with strong excess risk bounds.
method Output perturbation for a broad class of tilted loss functions.
result Near optimal DP excess risk and runtime bounds for convex optimization.

New algorithm improves gradient-based ERM for smooth convex losses.

problem Empirical risk minimization of smooth, strongly convex loss functions.
method Iterative gradient-based method with local polynomial regression.
result Oracle complexity of O((pε1)d/(2η))O((p ε^{-1})^{d/(2η)}) for our algorithm.

New algorithms achieve optimal DP convex optimization with linear time and gradient computations.

problem Private stochastic convex optimization with optimal excess loss.
method Two new techniques: variable batch sizes and localization with stable optimization.
result Achieves optimal bound on excess loss with O(min{n,n2/d})O(\min\{n, n^2/d\}) gradient computations.

One of the most effective algorithms for differentially private learning and optimization is objective perturbation. This technique augments a given optimization problem (e.g. deriving from an ERM problem) with a random linear term, and then exactly solves it. However, to date, analyses of this approach crucially rely …

2019-09-03abs ↗pdf ↗

This paper aims at refined error analysis for binary classification using support vector machine (SVM) with Gaussian kernel and convex loss. Our first result shows that for some loss functions such as the truncated quadratic loss and quadratic loss, SVM with Gaussian kernel can reach the almost optimal learning rate, p…

2017-02-28abs ↗pdf ↗

A new algorithm improves both computational efficiency and statistical optimality for robust low-rank matrix and tensor estimation.

problem Challenges in low-rank matrix estimation under heavy-tailed noise, both computationally and statistically.
method Riemannian sub-gradient (RsGrad) algorithm, which is computationally efficient and statistically optimal.
result RsGrad achieves linear convergence and statistical optimality for robust loss functions under Gaussian and heavy-tailed noise.

This paper advances FL algorithms for composite optimization and statistical recovery.

problem Federated learning optimization and statistical recovery in composite settings.
method Proposes Fast Federated Dual Averaging for strongly convex and smooth loss, and Multi-stage Federated Dual Averaging for restricted strongly convex and smooth loss.
result Establishes state-of-the-art iteration and communication complexity, and high probability complexity bound with linear speedup.

Adjusting the learning rate schedule in stochastic gradient methods is an important unresolved problem which requires tuning in practice. If certain parameters of the loss function such as smoothness or strong convexity constants are known, theoretical learning rate schedules can be applied. However, in practice, such …

2018-03-07abs ↗pdf ↗

New insights into training machine learning models with momentum.

problem Lack of theoretical understanding on the generalization error of momentum-based methods.
method Analyzed modified momentum-based update rule (SGDEM) for smooth Lipschitz loss functions.
result SGDEM admits an upper-bound on the generalization error for smooth Lipschitz loss functions.

New bounds for online portfolio selection without smoothness assumptions.

problem Online portfolio selection with non-Lipschitz, non-smooth losses.
method Data-dependent bounds using novel smoothness characterizations and FTRL with self-concordant regularizers.
result Achieves logarithmic regrets when data is 'easy' and sublinear worst-case regrets.

Paper relaxes stability and generalization assumptions for SGD.

problem Stability and generalization for SGD under restrictive assumptions.
method Introduces on-average model stability and develops novel bounds.
result First-ever-known fast bounds in low-noise setting using stability approach.

Paper addresses DP-SCO on heavy-tailed data, providing methods and results.

problem Designing DP algorithms for SCO on heavy-tailed data.
method Sample-and-aggregate framework, gradient smoothing and trimming.
result Achieved DP guarantees for various loss functions with different excess population risks.

Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.

problem The trade-off between smoothness and margin-based losses in classification and structured prediction.
method Linear-Core (LC) Surrogates, a family of convex loss functions that stitch a linear core to a smooth tail.
result LC Surrogates achieve fast linear consistency rates while maintaining differentiability and strict HH-consistency bounds.

Study on privacy leakage in noisy gradient descent algorithms.

problem Information leakage of iterative randomized learning algorithms about training data.
method Analyzes the dynamics of Rényi differential privacy loss in noisy gradient descent algorithms.
result Privacy loss converges exponentially fast for smooth and strongly convex loss functions.

New algorithm finds critical points in non-convex optimization with heavy-tailed gradients.

problem Non-convex stochastic optimization with heavy-tailed gradient estimates.
method Gradient clipping, momentum, and normalized gradient descent.
result High-probability convergence to critical points with best-known rates.

New algorithm achieves optimal privacy and efficiency in non-Euclidean convex optimization.

problem Optimizing convex functions while maintaining privacy in non-Euclidean settings.
method Developed a linear-time algorithm for p\ell_p-setups, leveraging geometric properties.
result Optimal excess risk achieved in linear time for 1<p21 < p \leq 2.

New algorithms minimize dynamic regret for strongly convex losses.

problem Minimizing dynamic regret for strongly convex losses.
method Developed Strongly Adaptive algorithms exploiting KKT conditions.
result Achieved near optimal dynamic regret of O(d1/3n1/3extTV[u1:n]2/3d)O(d^{1/3} n^{1/3} ext{TV}[u_{1:n}]^{2/3} \vee d).

New bounds for online convex optimization between stochastic and adversarial settings.

problem Understanding optimization tasks that are neither i.i.d. nor fully adversarial.
method Establishing novel regret bounds exploiting smoothness of expected losses.
result Regret bounds match expected rates in the fully i.i.d. case and gracefully deteriorate in the fully adversarial case.

Traditional dictionary learning methods are based on quadratic convex loss function and thus are sensitive to outliers. In this paper, we propose a generic framework for robust dictionary learning based on concave losses. We provide results on composition of concave functions, notably regarding super-gradient computati…

2017-11-02abs ↗pdf ↗

Stochastic GD converges linearly for CV@R learning under certain conditions.

problem Optimizing CV@R in statistical learning with non-convex loss functions.
method Stochastic Gradient Descent with Polyak-Łojasiewicz condition.
result Stochastic GD achieves linear convergence for CV@R learning.

We consider the fundamental problem in non-convex optimization of efficiently reaching a stationary point. In contrast to the convex case, in the long history of this basic problem, the only known theoretical results on first-order non-convex optimization remain to be full gradient descent that converges in $O(1/\varep…

2016-03-17abs ↗pdf ↗