- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes KOLO, a small family of executable challenges that retain or release intermediate representations to investigate the improvement available from a trained network. It establishes conditions for reconstructing untested route values, distinguishes reconstruction from threshold certification, and evaluates the approach through an exhaustive CIFAR-10 route census. The theoretical framework is systematic and offers useful conceptual distinctions. However, the applicability of its guarantees and the empirical evidence across architectures remain limited, while the experimental construction and attribution of LO's contribution require clarification. I therefore place the paper slightly below the acceptance threshold in its current form.
Critical strengths
The paper carefully distinguishes demonstrated improvement from certification and provides explicit counterexamples to unsupported extrapolation from a small route family. The graph-based identifiability analysis gives concrete recovery conditions. The exhaustive route census across three seeds and three checkpoints also exposes both successful and weaker settings.
Critical weaknesses
- Can the assumptions behind the core reconstruction guarantees be verified in practical neural networks?
The positive guarantees for route-value reconstruction require a coherent complete-model compiler, controlled unmodeled interactions, and identifiable route features. The paper reports the rank and condition number of the feature system, together with small empirical reconstruction errors. However, these results do not yet establish whether the theoretical error bounds are practically informative for trained nonlinear networks.
Could the authors provide a representative trained-network example showing how the compiler and route features satisfy the reconstruction conditions, and how valid bounds on unmodeled interactions and execution errors can be obtained without evaluating all routes? After substituting these quantities into Theorem~4, are the resulting reconstruction bounds sufficiently small relative to the achievable loss improvement? If a graph model restricts the allowed pairwise interactions, how is this structure determined, and how are excluded interactions accounted for in the error bounds? Small empirical reconstruction errors alone do not resolve these questions.
Furthermore, the neural-network experiments use only a CIFAR-10 residual classifier with smooth activations and spectral constraints, with . Could the authors add a targeted experiment using another architecture or relaxing these constraints to assess how headroom capture and reconstruction performance depend on these choices? For the further global conclusions, could the authors also clarify which solver, comparison-class, and coverage gaps are controlled in the experiments and which remain additional assumptions?
- How do the experimental compilers work, and how are the reconstruction and headroom experiments connected?
Section6 and AppendicesO--P name task-shaped and state-faithful compilers, under which KOLO captures 95.6% and 72.3% of exhaustive headroom, respectively. What optimization objectives and route-solving procedures do these compilers use, and how are retained representations enforced? A brief definition of both procedures would help explain this substantial difference.
AppendixP additionally introduces a separate frozen additive coupled compiler. Could the authors specify its feature system and relationship to the two compilers in Table4? Does the reconstruction experiment predict the same route values used to evaluate challenge strength, or a distinct route family?
- Does the task-shaped comparison distinguish the contributions of LO and route zero?
Section6 interprets the increase from KO's 88.5% mean capture to KOLO's 95.6% as evidence for LO's additional contribution. However, KOLO adds both LO and route zero. In the task-shaped panel of Figure3, the displayed LO capture never exceeds KO: for example, at seed/checkpoint , KO, LO, and KOLO capture approximately 84%, 0%, and 100%, respectively. Under the stated suite definitions, does this increase actually come from route zero rather than LO?
Could the authors report route zero alone and route zero plus KO to isolate LO's additional contribution and revise the attribution accordingly? The state-faithful results do contain LO improvements over KO; should this evidence be distinguished from the task-shaped comparison when discussing finite-budget complementarity?
Questions for authors
-
Is the compiler's optimization requirement in Appendix
A consistent with Definition2 and Section5? The terminology table says that the compiler agrees with route-constrained optima at Boolean vertices, whereas Definition2 does not require exact optimization and Section~5 allows a nonzero solver defect. Is exact optimality a necessary requirement, an additional assumption, or a special case? Could these descriptions be aligned? -
The figure captions and corresponding descriptions in the text do not match the plotted panels. Figure
2(c) compares reconstructable and pass-preserved route counts, but its caption and Section3.4 describe cubic error scaling. The relevant scaling plot is Figure4(b), whose reported fitted exponent of 2.88 indicates an approximately cubic trend over the tested range. The Figure4 caption also lists the KO value decomposition and monotone cross-crediting, whereas panels~(a) and~(b) show quadratic-truncation error with its upper bound and approximately cubic scaling for a contractive compiler. These captions and references should be corrected.
5 comments
W2. How the compilers work. Both hard-anchor compilers of Table 4 build a route the same way. The kept boundaries split the blocks into spans; each span starts from the checkpoint's weights and is fitted for 15 epochs on 20,000 training images, with the checkpoint's activation at its first boundary as input; the fitted spans are then chained into one network and evaluated on the audit split. The state-faithful compiler fits each span to reproduce the checkpoint's activation (or logits) at its last boundary and never sees labels. The task-shaped compiler adds 0.35 times the Brier loss of the span's output passed through the frozen checkpoint downstream (the last span is fitted to the labels alone).
Retained representations are therefore enforced softly, as fitting targets, and we measure the drift at every kept boundary. Its median stays at most 0.0025 for the state-faithful compiler. For the task-shaped compiler it grows from 0.018 with one kept boundary to 0.036 with eight, because each span is fitted against the frozen checkpoint downstream but feeds re-fitted spans in the assembled network. A task-shaped route's median audit Brier loss is accordingly within 0.001 of the checkpoint's with zero or one kept boundary, but 0.124 above it for LO routes and 0.150 above it with all eight kept. This explains most of the 95.6% versus 72.3% difference: under the task-shaped compiler the best route keeps at most two boundaries, a region route zero and KO cover, while under the state-faithful compiler it mostly keeps three, which KOLO lacks.
The coupled compiler. The checkpoint is frozen, and a repair vector (norm at most 0.08) is added after block whenever . The eight vectors are trained for 25 epochs on the 17 shell selectors only, and is then evaluated at all 256. Its feature system is the declared path-pair model, with , 16 features. It shares nothing with the two hard-anchor compilers: a coordinate switches a bounded repair rather than retaining a representation, and route zero is the checkpoint itself.
So the reconstruction experiment predicts a distinct route family, chosen because it satisfies Def. 2. The hard-anchor families do not, since their spans are fitted separately. Fitting the same 17-route model to them gives mixed results. Measured by the largest held-out error as a share of the range of route values, it is 10% to 89% (median 37%) on the coupled compiler, 25% to 67% (median 43%) on task-shaped routes, and 63% to 134% (median 91%) on state-faithful routes, with median rank correlations 0.81, 0.82 and 0.20. §6 will state that reconstruction and challenge strength are measured on different route families.
W3. Route zero versus LO. You are right. Under the task-shaped compiler, mean capture with the paper's convention (9 checkpoints) is: route zero 46.8%, KO 88.5%, LO 11.1%, route zero + KO 95.6%, KOLO 95.6%. No LO route improves on the checkpoint anywhere; LO's 11.1% comes only from the one checkpoint with no headroom at all, which the convention scores as 100% for every suite. The two checkpoints where KOLO exceeds KO, 0/80 (KO 84%, KOLO 100%) and 2/48 (KO 52%, KOLO 100%), are both captured by route zero. The increase from 88.5% to 95.6% therefore comes entirely from route zero. We will correct the attribution, add route zero and route zero + KO to Table 4, and also report means over the 8 checkpoints with positive headroom, where KOLO and route zero + KO both read 95.1%.
Under the state-faithful compiler, LO does add: route zero 5.7%, KO 63.6%, LO 33.7%, route zero + KO 65.7%, KOLO 72.3%. LO beats route zero + KO at 3 of 9 checkpoints, by 1, 22 and 35 points. We agree this is the evidence for finite-budget complementarity (Thm 9) and will discuss it separately from the task-shaped comparison.
Q1. Is exact optimality required? No. Reconstruction (Def. 2, Thms 3 and 4) needs only a single smooth compiler, and it reconstructs the compiler's own vertex values, whatever they are. Optimality enters only in §5, through the solver defect , when route evidence is transferred to the ideal route values of Def. 1. Agreement with the route-constrained optima at every vertex is the special case . The App. A terminology row is wrong and will read: "A single smooth map from to a complete model. Its vertex values need not be route-constrained optima; the gap is the solver defect of §5." For the coupled compiler of App. P, a vertex switches bounded repairs rather than imposing retention, so its values are compiler values and we make no optimality claim for them.
Q2. Figure captions. Thank you; the captions were not updated when the panels were regenerated. The corrections:
- Fig. 2(c): "Routes by cardinality whose values are reconstructable from the shell (signed identifiability) versus those preserved by shell passage (positive interpolation)." The §3.4 sentence citing Fig. 2(c) for cubic error scaling will cite Fig. 4(b) instead.
- Fig. 4: "(a) Quadratic-truncation error at every vertex, below the mixed-derivative certificate. (b) Contractive compiler: higher-order tail and certificate against route radius, with fitted small-radius slope 2.88, approximately cubic over the tested range. (c) At a matched finite budget, the LO gain stays at 0.5 while the KO gain falls as conditioning worsens, although exact KO is better. (d) Sharp collective-escape example: three hidden modes, each visible at every cut." Panels (c) and (d) match the current caption; the KO value decomposition and monotone cross-crediting, which no panel shows, will be removed from it.
Thank you for the detailed questions. We answer them from the existing census: all 256 routes at 9 checkpoints (3 seeds, epochs 20, 48 and 80) under both compilers, plus the coupled-compiler table. No new training was needed for any number below, and the script that produces them will be added to the supplement. W1 is answered here; W2, W3 and the two questions follow in the next comments.
W1. A trained-network example of the reconstruction conditions. The reconstruction theory is instantiated by the coupled compiler of App. P (defined in the next comment): one map from the selector x∈[0,1]8 to a complete model, smooth in x, with the 16-feature path-pair system and the 17 KOLO routes as design. At each checkpoint we computed the exact Möbius transform of all 256 values and every quantity in Thm 4.
So, to the direct question: at this scale the substituted bound is not small relative to the achievable improvement, and the revision will say so. What the reconstruction does support is choosing the next route to execute: running the one unobserved route the fitted model ranks best raises capture of the coupled headroom from 89.1% to 98.0%, against 93.0% for one random extra route. This needs no trust in the bound, because the nominated route is itself executed.
Bounds without evaluating all routes. From the shell alone, only the census-free envelope of App. E is a valid bound, and for this network it is too conservative to be informative: it grows as (1−q)−5 with worst-case block Lipschitz constant q=0.883, and in the controlled compiler it is about ten times the observed tail (Fig. 4(b)). Short of the census, the remainder can be estimated but not certified: the largest error over 8, 16 or 32 random held-out routes recovers on average 66%, 77% and 85% of the true largest error.
Graph structure and excluded interactions. The path graph was predeclared from the block order: consecutive boundaries are separated by a single block. Excluded pairs are not dropped; they enter the remainder of Thm 4 together with all higher-order terms, so the bound accounts for them, and the census shows they dominate it. Declaring all 28 pairs requires the 37 routes with ∣S∣≤2, after which the largest error is exactly the order-3 tail, a median 6.1 times smaller than the path model fitted to the shell. Thm 6 gives the minimal pair queries for any declared graph.
Other architectures and constraints. Within this network the census covers every sub-lattice of P′ monitored boundaries: over all 163 placements with P′ from 4 to 8, task-shaped KOLO capture stays at 95.1% to 95.6% while a random suite of the same size falls from 76% to 29%; state-faithful KOLO falls from 90% to 72% (random: 85% to 64%). The spectral constraint is needed only for the App. E envelope and smoothness only for the derivative bound of Thm 3; Thm 4 needs only the remainder, which a census measures for any architecture.
Solver, comparison-class and coverage gaps. Measured: τrec, τLCB and the anchor-residual part of εsol for all 4,608 route models. Assumed: the optimization part of εsol, εclass and δcov, which cannot be estimated from finitely many executions for a non-convex network and are computable exactly only in the deep-linear case (Thm 12). Every claim about the CIFAR-10 network is therefore route-level, and §6 will mark each term as measured, bounded or assumed.