Searcharxiv⌕ Search

arXiv subjects

Zeyu Jia

Publications and source records attributed to Zeyu Jia.

At least 19 recordsLinked to original sources

Cartesian Byte-Bank Models and Warp Lag Screening for GPU Lossless Compression

Headerless multi-channel 16-bit streams degrade unit-lag differencing, byte shuffling, and chunked GPU codecs when adjacent words belong to distinct sensors. On even-length 16-bit tiles (<= 16 MiB), GPX6 pairs a 32-lane CUDA warp lag screen with a threshold-free 3 x 2 Cartesian conditional byte-bank range Asymmetric Numeral Systems (rANS) coder and OpenMP Zstandard-1 framing. Across 30 subject-disjoint waveform files (88.90 MB, N = 27 subjects), GPX6 compresses to 26,449,754 B (29.75% aggregate; 42.68% subject mean; 40.74% six-cohort mean across 338.25 MB) at 424.1/279.0 MB/s host-to-host on RTX 4080 Laptop GPU and 266.9/166.4 MB/s on A100-80GB, reaching 474.1/482.3 MB/s (4.81/5.98 GB/s resident) on 30-tile A100 batches. Completing GPX4 into GPX6 saves +2.59 pp subject mean, localized to step-quantized BIDMC telemetry (+6.24 pp vs. +0.20 pp on smooth cohorts). Under 1-payload screening, GPX6 saves +10.59 pp ([+8.09, +13.28] pp) over faster zero-order GPU nvCOMP ANS, beats 16-bit MANS and 64 KiB nvCOMP Zstd (2.17x-2.49x faster encode), and maps CPU, audio, and 2D boundaries.

cs.AR↗

Beyond Embedding Transfer: Architectural Interfaces, Iso-Parameter Scaling, and Preconditioner-Governed Consolidation in Grokking

Grokking, or delayed generalization after memorization, incurs substantial training steps across algebraic tasks. Cross-operator transfer from a grokked donor accelerates target acquisition, yet post-grokking AdamW continuation triggers test-accuracy relapse as unannealed updates drift across residual interfaces and decaying second moments amplify late gradients. Across depths one to three on modular arithmetic ($\mathbb{Z}_{113}$), non-Abelian $S_5$ conjugation, and real-sensory MNIST modular arithmetic, we separate representational transfer from preconditioner-governed consolidation across thirteen experimental batteries. First, co-transferring internal blocks accelerates one-layer and two-layer modular takeoff beyond boundary interfaces, while graded prefix pinning bounds depth-three drift under unannealed continuation. Second, an iso-parameter $S_5$ scaling grid separates attention head dimension from MLP width: widening two-head attention to dimension $64$ reaches $98.54\%$ cold accuracy at $427\mathrm{k}$ parameters and $85.95\%$ boundary-only transfer, while final-slot representations refine conjugation directly across blocks without an intermediate binary-product bottleneck. Third, Plateau-Gated Leaky Consolidation pairs validation-envelope step damping with leaky second-moment decay, reaching $84.85\%$ zero-leakage validation-gated risk-constrained accuracy across five pre-saturation two-layer $S_5$ suites while cutting step budget relative to hard anchoring. Fourth, transferring a grokked visual trunk and blocks to image-disjoint MNIST targets reaches $92.27\%$ and $90.76\%$ accuracy, prunes odd centroid harmonics, and reaches $90.42\%$ risk-constrained accuracy across $60/60$ branches without hyperparameter retuning.

cs.LG↗

Symmetry-Induced Conservation Laws, Three-Channel Attribution, and Solid-Phase Recycling in Prebiotic Enantiomeric Excess Amplification

Enantiomeric excess is the primary observable used to quantify chiral amplification across prebiotic chemistry, asymmetric autocatalysis, and multiphase crystallization. Because enantiomeric excess divides net chiral excess by total chiral mass, identical increases can arise either from parity-breaking synthesis of chiral centers or from symmetric phase and oligomer partitioning that depletes soluble mass. We establish a pathwise conservation law, a model-free three-channel attribution identity, and a continuous path-covariant Aumann--Shapley attribution for mirror-symmetric reaction networks. In any closed network lacking autocatalytic feedback or epimerization, net chiral excess remains invariant along every stochastic trajectory, locking liquid-phase amplification inversely to surviving chiral mass while Shear--Kramers--Lorentz relative-entropy balance bounds dissipation. We re-analyze seven experimental benchmark systems and show that standalone phase removal loses $91.7\%$--$98.9\%$ of chiral solute into racemic sediment in closed batches and washes out under open racemic inflow. We show that coupling eutectic partitioning with racemization recycling achieves $96.5\%$ homochiral crystal recovery, whereas evaporative autocatalysis crosses the open-flow bifurcation threshold with $81.9\%$ homochiral yield. Finally, we extend our non-crossing parity invariant across a fifty-nine-point multicomponent peptide ligation and seeded co-precipitation benchmark, evaluate a one-hundred-twelve-row calcite adsorption dataset, and resolve mineral-occlusion non-identifiability using three-block antipodal crystal pairs.

q-bio.BM↗

Typed Edge-Tensor Non-Reciprocal Port-Hamiltonian Deliberation for Counterfactual Open-World Deductive Reasoning

Scaling test-time computation in continuous latent spaces offers an attractive alternative to verbose token-by-token generation for multi-step deductive reasoning. However, unregularized recurrent latent updates suffer from a deliberation drift cliff when rolled out beyond training horizons, while strictly energy-conserving or symmetric message-passing dynamics cannot break parent-to-child causal symmetry or suppress cyclic modus-ponens amplification on cyclic distraction graphs. We introduce Typed Edge-Tensor Non-Reciprocal Port-Hamiltonian Deliberation (TE-BPHD), a neuro-symbolic continuous-time latent reasoning architecture that couples skew-symmetric port-Hamiltonian conservation with relation-typed non-reciprocal directional transport and monotone dissipative damping on a semantic entity-state manifold. We prove (i) unconditional input-to-state stability and exponential contraction of autonomous rollouts across arbitrary inference depths without external norm projection, (ii) strict directional DAG reachability separation over symmetric message passing, and (iii) exact cycle-suppression margins under finite cyclic horn perturbations. Across counterfactual open-world deductive benchmarks (PrOntoQA-OOD up to depth 15, ProofWriter-OWA Cyclic at depths 5-10, FOLIO-Symbolic, and Cluttr-Relational), TE-BPHD eliminates the deep-horizon drift cliff, improves depth-10 cyclic reasoning accuracy to 90.0% (+/- 0.8%) over symmetric port-Hamiltonian and standard Transformer baselines, and supports zero-retraining adaptive Lyapunov halting that reduces average solver evaluations by 44% with negligible accuracy loss.

cs.LG↗

Non-Commutative Lie-Algebraic State-Space Models: Finite-Division Variety Laws, Semidirect Cascades, and Gradient Saddle Escape

Structured state-space sequence models (SSMs) achieve linear-time inference and logarithmic-time parallel training via associative scans, yet diagonal transitions generate solvable semigroups unable to track non-solvable group words or 3D rigid-body manifolds. We present Non-Commutative Lie-Algebraic State-Space Models (Lie-SSMs), parameterizing recurrent updates on Lie algebra tangent spaces via the matrix exponential. First, using an o-minimal cylindrical flag collar, we establish an unconditional single-layer finite-division criterion for contracting $SO(3)$ and $SU(2)$ heads, proving odd-prime Sylow abelianity, odd-$p$-core centrality, and exponent-30 commutator obstructions excluding $S_5$ in $SO(3)^m, SU(2)^m,$ and $SO(4)^m$ while identifying the sharp threshold $d^*(S_5)=d^*(A_6)=5$ in $SO(5)$. Second, Depth-2 semidirect and Schreier $2$-cocycle cascades resolve $S_5$, $2I\cong SL_2(F_5)$, and $\mathrm{Heis}(F_p)$ in $O(\log T)$ scan depth, whereas unnormalized contracting coupling collapses exponentially without Directional RMSNorm. Third, we characterize the $Θ(\varepsilon^{c-1})$ Chen--Magnus--Hall--Witt commutator saddle and $1/|[G,G]|$ coset-centroid dilution, proving generic first-order symmetry breaking at $\varepsilon=0$ and teacher-forced local Polyak--Łojasiewicz convergence under dense prefix supervision and factored readouts ($99.90\%/99.40\%$ on $S_5$ at $T=128$; $100.00\%$ on $D_{16}$). Across $SE_2(3)$ Left-Jacobian odometry, Hillis--Steele/Blelloch GPU scans ($48.24\times$ forward, $20.27\times/10.28\times$ full-layer speedup at $T=2048$), and three 3D IMU benchmarks (UCI HAR, UCI HAPT-PT, and 17-subject REALDISP), Lie-$SO(3)$ models reach $95.69\%\pm 0.14\%$ on HAR, $88.44\%\pm 0.83\%$ episode logit-vote ($83.97\%\pm 1.20\%$ C3 window in 30-subject 5-fold CV; $87.16\%\pm 0.64\%$ 9-subject split) on HAPT-PT, and $84.23\%\pm 1.00\%$ on REALDISP.

cs.LG↗

Sub-Voxel Displacement and Ipsilateral Territory Decoupling for 3D Bilateral Coronary Artery Tree Reconstruction in Cardiac CT Angiography

Reconstructing topologically complete, sub-voxel-accurate 3D bilateral coronary artery trees from cardiac CT angiography (CCTA) requires simultaneously recovering continuous centerline trajectories and separating dense left/right coronary territories without cross-ostial collisions. We present a five-stage tubular drift and ipsilateral territory decoupling framework (M1-M5). Stage M1 pairs a 398,843-parameter multi-scale 3D pyramid encoder with a four-head tubular field network predicting vesselness probability, signed tubular boundary distance, unit tangent vectors, and continuous 3D centripetal displacement vectors. Stage M2 introduces recall-preserving multi-task optimization with 7-group AdamW parameter decoupling, L2-SP backbone regularization, and per-step anchor shrinkage. Stage M3 calibrates cylindrical Valsalva-sinotubular-junction wall coordinates and native-resolution orifice contact expectations for robust left and right ostial rooting. Stage M4 constructs a scalar-potential-weighted minimum-cost arborescence followed by normal-plane cross-sectional pullback and centripetal trajectory pruning. Stage M5 enforces coverage-guarded ipsilateral-field-coupled bilateral collision reduction and subtree handover. Across a 14-case held-out development cohort (Dev-14, 17-arm forward incremental build and 9-arm leave-one-out ablation) and an independent 50-case out-of-sample evaluation cohort (OOS-50) benchmarked against seven external architectures (nnU-Net, 3D UX-Net, Swin-UNETR, MedNeXt, CS2-Net, clDice-UNet, and Point-UNet), M1-M5 reduces bilateral chamfer distance on Dev-14 from 3.4381 mm to 2.2759 mm and achieves 2.7671 mm on OOS-50 with 7.11% bilateral collision rate and 79.7% distal branch completeness.

cs.CV↗

Steady symmetric Navier-Stokes flow near Poiseuille flow: existence and vanishing viscosity limit

We study the existence and vanishing viscosity limit of steady incompressible Navier-Stokes flows in a horizontally periodic strip with no slip boundary conditions and midline symmetric forcing. Taking a Poiseuille flow as the leading order Euler profile, we construct higher order symmetric approximate solutions and establish the existence of a symmetric solution to the associated nonlinear error equation. Under suitable compatibility conditions on the forcing, this construction yields a family of midline symmetric steady Navier-Stokes solutions that converges to the prescribed Poiseuille flow at the optimal rate.

math.AP↗

Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning

Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisit the classical paradigm of Bellman Residual Minimization and introduce Trajectory Bellman Residual Minimization (TBRM), an algorithm that naturally adapts this idea to LLMs, yielding a simple yet effective off-policy algorithm that optimizes a single trajectory-level Bellman objective using the model's own logits as $Q$-values. TBRM removes the need for critics, importance-sampling ratios, or clipping, and operates with only one rollout per prompt. We prove convergence to the near-optimal KL-regularized policy from arbitrary off-policy data via an improved change-of-trajectory-measure analysis. Experiments on standard mathematical-reasoning benchmarks show that TBRM consistently outperforms policy-based baselines, like PPO and GRPO, with comparable or lower computational and memory overhead. Our results indicate that value-based RL might be a principled and efficient alternative for enhancing reasoning capabilities in LLMs.

cs.LG↗

Testing and estimation in orthosymmetric Gaussian sequence model

We study the Gaussian sequence model, i.e. $X \sim N(\mathbfθ, I_\infty)$, where $\mathbfθ \in Γ\subset \ell_2$ is assumed to be convex and compact. We show that goodness-of-fit testing sample complexity is lower bounded by the square-root of the estimation complexity, whenever $Γ$ is orthosymmetric. This lower bound is tight when $Γ$ is also quadratically convex (as shown by [Donoho et al. 1990, Neykov 2023]). We also completely characterize likelihood-free hypothesis testing (LFHT) complexity for $\ell_p$-bodies, discovering new types of tradeoff between the numbers of simulation and observation samples, compared to the case of ellipsoids (p = 2) studied in [Gerber and Polyanskiy 2024].

math.ST↗

A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity

We study gapped scale-sensitive dimensions of a function class in both sequential and non-sequential settings. We demonstrate that covering numbers for any uniformly bounded class are controlled above by these gapped dimensions, generalizing the results of \cite{anthony2000function,alon1997scale}. Moreover, we show that the gapped dimensions lead to lower bounds on offset Rademacher averages, thereby strengthening existing approaches for proving lower bounds on rates of convergence in statistical and online learning.

stat.ML↗

Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

Reinforcement learning with outcome-based feedback faces a fundamental challenge: when rewards are only observed at trajectory endpoints, how do we assign credit to the right actions? This paper provides the first comprehensive analysis of this problem in online RL with general function approximation. We develop a provably sample-efficient algorithm achieving $\widetilde{O}({C_{\rm cov} H^3}/{ε^2})$ sample complexity, where $C_{\rm cov}$ is the coverability coefficient of the underlying MDP. By leveraging general function approximation, our approach works effectively in large or infinite state spaces where tabular methods fail, requiring only that value functions and reward functions can be represented by appropriate function classes. Our results also characterize when outcome-based feedback is statistically separated from per-step rewards, revealing an unavoidable exponential separation for certain MDPs. For deterministic MDPs, we show how to eliminate the completeness assumption, dramatically simplifying the algorithm. We further extend our approach to preference-based feedback settings, proving that equivalent statistical efficiency can be achieved even under more limited information. Together, these results constitute a theoretical foundation for understanding the statistical properties of outcome-based reinforcement learning.

cs.LG↗

Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective

As large language models have evolved, it has become crucial to distinguish between process supervision and outcome supervision -- two key reinforcement learning approaches to complex reasoning tasks. While process supervision offers intuitive advantages for long-term credit assignment, the precise relationship between these paradigms has remained an open question. Conventional wisdom suggests that outcome supervision is fundamentally more challenging due to the trajectory-level coverage problem, leading to significant investment in collecting fine-grained process supervision data. In this paper, we take steps towards resolving this debate. Our main theorem shows that, under standard data coverage assumptions, reinforcement learning through outcome supervision is no more statistically difficult than through process supervision, up to polynomial factors in horizon. At the core of this result lies the novel Change of Trajectory Measure Lemma -- a technical tool that bridges return-based trajectory measure and step-level distribution shift. Furthermore, for settings with access to a verifier or a rollout capability, we prove that any policy's advantage function can serve as an optimal process reward model, providing a direct connection between outcome and process supervision. These findings suggest that the empirically observed performance gap -- if any -- between outcome and process supervision likely stems from algorithmic limitations rather than inherent statistical difficulties, potentially transforming how we approach data collection and algorithm design for reinforcement learning.

cs.LG↗

On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy

We study the problem of sequential probability assignment under logarithmic loss, both with and without side information. Our objective is to analyze the minimax regret -- a notion extensively studied in the literature -- in terms of geometric quantities, such as covering numbers and scale-sensitive dimensions. We show that the minimax regret for the case of no side information (equivalently, the Shtarkov sum) can be upper bounded in terms of sequential square-root entropy, a notion closely related to Hellinger distance. For the problem of sequential probability assignment with side information, we develop both upper and lower bounds based on the aforementioned entropy. The lower bound matches the upper bound, up to log factors, for classes in the Donsker regime (according to our definition of entropy).

cs.LG↗

Rate of convergence of the smoothed empirical Wasserstein distance

Consider an empirical measure $\mathbb{P}_n$ induced by $n$ iid samples from a $d$-dimensional $K$-subgaussian distribution $\mathbb{P}$ and let $γ= N(0,σ^2 I_d)$ be the isotropic Gaussian measure. We study the speed of convergence of the smoothed Wasserstein distance $W_2(\mathbb{P}_n * γ, \mathbb{P}*γ) = n^{-α+ o(1)}$ with $*$ being the convolution of measures. For $K<σ$ and in any dimension $d\ge 1$ we show that $α= {1\over2}$. For $K>σ$ in dimension $d=1$ we show that the rate is slower and is given by $α= {(σ^2 + K^2)^2\over 4 (σ^4 + K^4)} < 1/2$. This resolves several open problems in [GGNWP20], and in particular precisely identifies the amount of smoothing $σ$ needed to obtain a parametric rate. In addition, for any $d$-dimensional $K$-subgaussian distribution $\mathbb{P}$, we also establish that $D_{KL}(\mathbb{P}_n * γ\|\mathbb{P}*γ)$ has rate $O(1/n)$ for $K<σ$ but only slows down to $O({(\log n)^{d+1}\over n})$ for $K>σ$. The surprising difference of the behavior of $W_2^2$ and KL implies the failure of $T_{2}$-transportation inequality when $σ< K$. Consequently, it follows that for $K>σ$ the log-Sobolev inequality (LSI) for the Gaussian mixture $\mathbb{P} * N(0, σ^{2})$ cannot hold. This closes an open problem in [WW+16], who established the LSI under the condition $K<σ$ and asked if their bound can be improved.

math.PR↗

How Does Variance Shape the Regret in Contextual Bandits?

We consider realizable contextual bandits with general function approximation, investigating how small reward variance can lead to better-than-minimax regret bounds. Unlike in minimax bounds, we show that the eluder dimension $d_\text{elu}$$-$a complexity measure of the function class$-$plays a crucial role in variance-dependent bounds. We consider two types of adversary: (1) Weak adversary: The adversary sets the reward variance before observing the learner's action. In this setting, we prove that a regret of $Ω(\sqrt{\min\{A,d_\text{elu}\}Λ}+d_\text{elu})$ is unavoidable when $d_{\text{elu}}\leq\sqrt{AT}$, where $A$ is the number of actions, $T$ is the total number of rounds, and $Λ$ is the total variance over $T$ rounds. For the $A\leq d_\text{elu}$ regime, we derive a nearly matching upper bound $\tilde{O}(\sqrt{AΛ}+d_\text{elu})$ for the special case where the variance is revealed at the beginning of each round. (2) Strong adversary: The adversary sets the reward variance after observing the learner's action. We show that a regret of $Ω(\sqrt{d_\text{elu}Λ}+d_\text{elu})$ is unavoidable when $\sqrt{d_\text{elu}Λ}+d_\text{elu}\leq\sqrt{AT}$. In this setting, we provide an upper bound of order $\tilde{O}(d_\text{elu}\sqrtΛ+d_\text{elu})$. Furthermore, we examine the setting where the function class additionally provides distributional information of the reward, as studied by Wang et al. (2024). We demonstrate that the regret bound $\tilde{O}(\sqrt{d_\text{elu}Λ}+d_\text{elu})$ established in their work is unimprovable when $\sqrt{d_{\text{elu}}Λ}+d_\text{elu}\leq\sqrt{AT}$. However, with a slightly different definition of the total variance and with the assumption that the reward follows a Gaussian distribution, one can achieve a regret of $\tilde{O}(\sqrt{AΛ}+d_\text{elu})$.

cs.LG↗

Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data

We revisit the problem of offline reinforcement learning with value function realizability but without Bellman completeness. Previous work by Xie and Jiang (2021) and Foster et al. (2022) left open the question whether a bounded concentrability coefficient along with trajectory-based offline data admits a polynomial sample complexity. In this work, we provide a negative answer to this question for the task of offline policy evaluation. In addition to addressing this question, we provide a rather complete picture for offline policy evaluation with only value function realizability. Our primary findings are threefold: 1) The sample complexity of offline policy evaluation is governed by the concentrability coefficient in an aggregated Markov Transition Model jointly determined by the function class and the offline data distribution, rather than that in the original MDP. This unifies and generalizes the ideas of Xie and Jiang (2021) and Foster et al. (2022), 2) The concentrability coefficient in the aggregated Markov Transition Model may grow exponentially with the horizon length, even when the concentrability coefficient in the original MDP is small and the offline data is admissible (i.e., the data distribution equals the occupancy measure of some policy), 3) Under value function realizability, there is a generic reduction that can convert any hard instance with admissible data to a hard instance with trajectory data, implying that trajectory data offers no extra benefits over admissible data. These three pieces jointly resolve the open problem, though each of them could be of independent interest.

cs.LG↗

When is Agnostic Reinforcement Learning Statistically Tractable?

We study the problem of agnostic PAC reinforcement learning (RL): given a policy class $Π$, how many rounds of interaction with an unknown MDP (with a potentially large state and action space) are required to learn an $ε$-suboptimal policy with respect to $Π$? Towards that end, we introduce a new complexity measure, called the \emph{spanning capacity}, that depends solely on the set $Π$ and is independent of the MDP dynamics. With a generative model, we show that for any policy class $Π$, bounded spanning capacity characterizes PAC learnability. However, for online RL, the situation is more subtle. We show there exists a policy class $Π$ with a bounded spanning capacity that requires a superpolynomial number of samples to learn. This reveals a surprising separation for agnostic learnability between generative access and online access models (as well as between deterministic/stochastic MDPs under online access). On the positive side, we identify an additional \emph{sunflower} structure, which in conjunction with bounded spanning capacity enables statistically efficient online RL via a new algorithm called POPLER, which takes inspiration from classical importance sampling methods as well as techniques for reachable-state identification and policy evaluation in reward-free exploration.

cs.LG↗

Entropic characterization of optimal rates for learning Gaussian mixtures

We consider the question of estimating multi-dimensional Gaussian mixtures (GM) with compactly supported or subgaussian mixing distributions. Minimax estimation rate for this class (under Hellinger, TV and KL divergences) is a long-standing open question, even in one dimension. In this paper we characterize this rate (for all constant dimensions) in terms of the metric entropy of the class. Such characterizations originate from seminal works of Le Cam (1973); Birge (1983); Haussler and Opper (1997); Yang and Barron (1999). However, for GMs a key ingredient missing from earlier work (and widely sought-after) is a comparison result showing that the KL and the squared Hellinger distance are within a constant multiple of each other uniformly over the class. Our main technical contribution is in showing this fact, from which we derive entropy characterization for estimation rate under Hellinger and KL. Interestingly, the sequential (online learning) estimation rate is characterized by the global entropy, while the single-step (batch) rate corresponds to local entropy, paralleling a similar result for the Gaussian sequence model recently discovered by Neykov (2022) and Mourtada (2023). Additionally, since Hellinger is a proper metric, our comparison shows that GMs under KL satisfy the triangle inequality within multiplicative constants, implying that proper and improper estimation rates coincide.

math.ST↗