Average Oracle outperforms DCC+NLS in portfolio optimization.
problem Optimizing portfolio performance in volatile markets.
method Comparing the Average Oracle to various DCC+NLS variants.
result The Average Oracle consistently yields higher Sharpe ratios.
Enhances UPSA to reduce noise in financial data.
problem Noise in financial data affects UPSA's performance.
method Time-averaging optimal penalty weights and using Average Oracle correlation eigenvalues.
result Combining time-averaging and Average Oracle correlation eigenvalues improves UPSA's performance.
Improved stochastic Halpern iteration for fixed-point approximation in normed spaces.
problem Approximating fixed-points of nonexpansive and contractive operators in normed finite-dimensional spaces.
method Stochastic Halpern iteration with minibatch, analyzing oracle complexity.
result Improved oracle complexity for nonexpansive operators, with a lower bound of Ω ( ε − 3 ) Ω(\varepsilon^{-3}) Ω ( ε − 3 ) . New averaging technique speeds up Newton method convergence.
problem Superlinear convergence of stochastic Newton methods with noisy Hessians.
method Hessian averaging to reduce noise and maintain superlinear convergence.
result Hessian averaging achieves superlinear convergence with a non-asymptotic rate.
New model-free RL algorithm tackles robust average-reward problems with finite sample complexity analysis.
problem Long-term decision-making in environments with varying dynamics.
method Proposes Robust Halpern Iteration (RHI) algorithm based on a black-box sampling oracle and multi-level Monte-Carlo estimator.
result Achieves ε-optimal robust policy with sample complexity of O(1/ε^(2+o(1))) under generative model setting.
This paper studies the lower bound complexity for the optimization problem whose objective function is the average of n n n individual smooth convex functions. We consider the algorithm which gets access to gradient and proximal oracle for each individual component. For the strongly-convex case, we prove such an algorith…
We provide tight upper and lower bounds on the complexity of minimizing the average of m m m convex functions using gradient and prox oracles of the component functions. We show a significant gap between the complexity of deterministic vs randomized optimization. For smooth functions, we show that accelerated gradient de…
EP-learning framework improves causal contrast estimation efficiency.
problem Estimating heterogeneous causal contrasts efficiently and stably.
method EP-learning framework combining T-learning and DR-learning.
result EP-learners are oracle-efficient and outperform competitors.
A robust aggregation method improves federated learning's accuracy in corrupted settings.
problem Making federated learning robust to corrupted updates from devices.
method Robust aggregation oracle based on geometric median for constant iterations of non-robust averaging.
result The robust aggregation oracle outperforms classical methods in high corruption levels.
The paper addresses model averaging and ensembling, providing theoretical and practical insights.
problem Combining least squares estimators from multiple candidate models for improved predictive accuracy.
method Establishes oracle inequalities for Mallows' C p C_p C p criterion, proposes a novel Mallows-type MA procedure. result Demonstrates the effectiveness of the proposed Mallows-type MA estimator through numerical experiments.
Paper establishes lower bounds for finite-sum optimization problems using novel construction methods.
problem Lower complexity bounds for finite-sum optimization problems with various component functions.
method Developed novel approach to construct hard instances and analyzed PIFO algorithms.
result Established lower complexity bounds for convex-concave and nonconvex-strongly-concave objectives.
CJE calibrates cheap LLM judges against an oracle, achieving high accuracy at a fraction of the cost.
problem Inexpensive LLM judges can produce biased rankings, leading to unreliable outcomes.
method CJE uses a small oracle to calibrate cheap scores, then evaluates at scale with valid uncertainty.
result CJE achieves 99% pairwise ranking accuracy at 14x lower cost compared to a 16x oracle/judge cost ratio.
Proposes P-learner for estimating treatment effects with proxy variables.
problem Estimating treatment effect heterogeneity in settings with unverifiable exchangeability.
method Two-stage loss function for learning heterogeneous treatment effects with proxy variables.
result P-learner satisfies an oracle bound on estimated error.
Adapts to misspecification in contextual bandits using offline regression.
problem Unexpected regret due to misspecified reward models.
method Adapts to misspecification by reverting to a safe policy when necessary.
result Regret guarantees degrade gracefully with misspecification level.
Estimates CATEs for structured treatments using a new decomposition method.
problem Estimating conditional average treatment effects for complex data types.
method Generalized Robinson decomposition, isolating causal estimand, arbitrary model plugging, quasi-oracle convergence guarantee.
result Demonstrates superior performance in CATE estimation compared to prior work.
This paper optimizes liquidation strategies in DeFi protocols to prevent MEV attacks.
problem Predatory price manipulations and Maximal Extractable Value (MEV) attacks in DeFi protocols.
method Dynamic program modeling, Constant Product Market Maker (CPMM) transaction fees analysis.
result CPMM transaction fees make liquidation manipulations unprofitable for attackers.
The paper explores MAB strategies for very short horizons, introducing new methods and showing improved performance.
problem Short horizon multi-armed bandit problems in games.
method Regression oracles, forced exploration, UCBT strategy.
result Combination of epsilon-greedy or epsilon-decreasing with regression oracles outperforms other strategies.
New research shows SAA can outperform SA for Wasserstein barycenters.
problem Optimizing Wasserstein barycenters with entropy regularization.
method Comparison of Stochastic Approximation (SA) and Sample Average Approximation (SAA) for large-scale problems.
result SAA can be more efficient than SA for Wasserstein barycenters, especially in large-scale settings.
CDST improves ensemble prediction by adjusting model weights based on covariates.
problem Improving ensemble prediction accuracy in complex scenarios.
method Covariate-dependent stacking (CDST) with flexible model weights estimated via cross-validation.
result CDST consistently outperforms conventional model averaging methods in complex datasets.
Paper develops methods for non-quadratic loss low-rank matrix recovery.
problem Recovery of low-rank matrices with non-quadratic losses.
method Projected gradient method with a regularity projection oracle.
result Projected gradient method converges globally and linearly.
Improved stochastic optimization outperforms standard methods.
problem Optimizing smooth, strongly convex functions with noisy data.
method Variance reduction strategy called VISOR.
result VISOR achieves optimal sample complexity and oracle complexity.
New method improves transductive learning predictions with multiplicative oracle inequalities.
problem Improving transductive learning predictions with known covariates.
method Median of Level-Set Aggregation (MLSA) for transductive LOO prediction.
result Proved multiplicative oracle inequality for LOO error.
New algorithm reduces regret in online learning for piecewise continuous functions.
problem Exponential loss in efficiency when moving from classical to adversarial learning.
method Introduces generalized bracketing numbers and Follow-the-Perturbed-Leader algorithm.
result Optimal scaling of optimization oracle calls with average regret.
New algorithm optimizes stochastic optimization with circular dependency.
problem Circular dependency between decision variable and importance sampling.
method Single-loop stochastic approximation algorithm based on Nesterov's dual averaging.
result Achieves minimal asymptotic variance and resolves circular optimization challenge.
Aggregated hold-out (Agghoo) is a method which averages learning rules selected by hold-out (that is, cross-validation with a single split). We provide the first theoretical guarantees on Agghoo, ensuring that it can be used safely: Agghoo performs at worst like the hold-out when the risk is convex. The same holds true…
New algorithms find optimal policies without knowing MDP span.
problem Finding optimal policies in MDPs without knowing span.
method Horizon calibration and span penalization techniques.
result First algorithms achieving optimal span-based complexity without prior knowledge.
New methods solve optimization problems with heavy-tailed noise, improving upon existing complexity bounds.
problem Optimization problems with heavy-tailed noise and weakly average smoothness.
method Normalized stochastic first-order methods with Polyak, multi-extrapolated, and recursive momentum.
result First-order oracle complexity results for finding approximate stochastic stationary points under heavy-tailed noise.
New algorithms optimize actions under time-varying constraints without projecting.
problem Optimizing actions under time-varying constraints without projecting.
method Projection-free algorithms using linear optimization oracle.
result Guaranteed i l d e O ( T 3 / 4 ) ilde{O}(T^{3/4}) i l d e O ( T 3/4 ) regret and O ( T 7 / 8 ) O(T^{7/8}) O ( T 7/8 ) constraints violation. Paper proves optimality of doubly robust estimators for treatment effects.
problem Estimating treatment effects in causal inference.
method Structure-agnostic framework of statistical lower bounds, using non-parametric regression and classification oracles.
result Doubly robust estimators are statistically optimal for ATE and ATT.
B-Learner provides bounds on CATE under hidden confounding risks.
problem Estimating CATE in the presence of hidden confounding.
method Adapting bounds on average treatment effect to conditional distributional treatment effects.
result B-Learner offers valid, sharp, efficient, and quasi-oracle bounds on CATE.
Optimal CATE estimation with structured contrast functions using KRR.
problem Estimating CATEs with complex response functions in RKHS.
method Unified two-stage kernel ridge regression method for structured contrast functions.
result Minimax rates governed by contrast function complexity, enabling adaptation.
We propose a computationally efficient estimator, formulated as a convex program, for a broad class of non-linear regression problems that involve difference of convex (DC) non-linearities. The proposed method can be viewed as a significant extension of the "anchored regression" method formulated and analyzed in [10] f…
A new federated learning algorithm improves on existing methods by exploiting data smoothness.
problem Federated learning optimization with smooth loss functions.
method Federated Low Rank Gradient Descent (FedLRGD) algorithm.
result FedLRGD outperforms Federated Averaging (FedAve) in federated oracle complexity under certain conditions.
Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costly or time consuming. In this paper, we address a new problem of active…
New algorithms solve complex multi-level optimization problems with improved efficiency.
problem Smooth stochastic multi-level composition optimization problems.
method Two algorithms using moving-average and linearized stochastic estimates.
result Achieved sample complexities of O(1/ε^4) and O(1/ε^6).
Paper tackles NNS under uncertainty with improved algorithms.
problem Efficient nearest neighbor search with noisy distance estimates.
method Combines cover trees and multi-armed bandits for optimal performance.
result Optimal dependence on dataset size and unknown geometry achieved.
Proposes a framework for selecting machine learning algorithms in semiparametric models.
problem Model selection in semiparametric problems with high-dimensional nuisance parameters.
method Selective machine learning framework based on a novel pseudo-risk criterion.
result Empirical selection criterion performs nearly as well as an oracle in cross-validation.
New stability bounds for GD in overparameterised shallow nets without NTK assumptions.
problem Generalisation and excess risk bounds for shallow neural networks.
method Oracle inequalities and stability analysis of GD without kernelisation.
result Oracle type bounds reveal GD's generalisation is controlled by an interpolating network with shortest GD path.
Many machine learning, statistical inference, and portfolio optimization problems require minimization of a composition of expected value functions (CEVF). Of particular interest is the finite-sum versions of such compositional optimization problems (FS-CEVF). Compositional stochastic variance reduced gradient (C-SVRG)…
We consider a problem of manifold estimation from noisy observations. Many manifold learning procedures locally approximate a manifold by a weighted average over a small neighborhood. However, in the presence of large noise, the assigned weights become so corrupted that the averaged estimate shows very poor performance…
New method improves CATE model selection with optimal regret rates.
problem Nontrivial task of selecting accurate CATE models.
method Causal Q-aggregation using doubly robust loss.
result Achieves optimal oracle model selection regret rates of log(M)/n.
New algorithm learns POMDPs with known observation model efficiently.
problem Learning POMDPs with unknown transition model in average-reward setting.
method OAS estimation technique and OAS-UCRL algorithm balancing exploration-exploitation.
result Regret guarantee of order O ( T log ( T ) ) \mathcal{O}(\sqrt{T \log(T)}) O ( T log ( T ) ) for OAS-UCRL algorithm. A game-theoretic analysis of DEX competition through dynamic trading fees.
problem Competition between decentralized exchanges (DEXs) and their impact on trading fees and slippage.
method Characterization of an approximate Nash equilibrium via coupled system of partial differential equations and closed-form expressions for equilibrium fees.
result The equilibrium trading fees shift from the oracle price to a weighted average of the oracle and competitors' exchange rates under competition.
Oracle-efficient algorithms reduce combinatorial semi-bandit regret to logarithmic time.
problem Scalability issue in combinatorial semi-bandit problems due to high combinatorial optimization costs.
method Oracle-efficient frameworks that minimize oracle queries while maintaining tight regret guarantees.
result Achieved i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) regret with O ( log log T ) O(\log\log T) O ( log log T ) oracle queries for worst-case linear rewards. We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes physical and cognitive limitations of the oracle into account when selecting sensor data to be annotated by the oracle. Our approach is inspired by human-beings' limited capacity to respond …
New analysis shows Thompson Sampling can work with greedy approximations in combinatorial bandits.
problem Thompson Sampling's theoretical limits with greedy approximations in combinatorial semi-bandits.
method Study with greedy oracle, providing lower and upper bounds on regret.
result First theoretical results showing TS can work with greedy approximations, breaking misconceptions.
New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.
problem Sampling uniformly from convex bodies efficiently.
method Markov chain Monte Carlo with proximal sampler and restricted Gaussian oracle.
result Efficient implementation of RGO for uniform sampling on convex bodies.
MAMBA learns policies competitive with multiple conflicting oracles.
problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.